Search Results for author: Pascal Fua

Found 148 papers, 44 papers with code

Towards Reliable Evaluation of Algorithms for Road Network Reconstruction from Aerial Images

no code implementations ECCV 2020 Leonardo Citraro, Mateusz Koziński, Pascal Fua

Existing connectivity-oriented performance measures rank road delineation algorithms inconsistently, which makes it difficult to decide which one is best for a given application.

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

no code implementations29 Mar 2022 Soumava Kumar Roy, Leonardo Citraro, Sina Honari, Pascal Fua

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant.

3D Human Pose Estimation 3D Pose Estimation

Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation

no code implementations18 Mar 2022 Yinlin Hu, Pascal Fua, Mathieu Salzmann

Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction.

6D Pose Estimation using RGB

Adversarial Parametric Pose Prior

no code implementations8 Dec 2021 Andrey Davydov, Anastasia Remizova, Victor Constantin, Sina Honari, Mathieu Salzmann, Pascal Fua

The Skinned Multi-Person Linear (SMPL) model can represent a human body by mapping pose and shape parameters to body meshes.

3D Reconstruction

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

no code implementations6 Dec 2021 Doruk Oner, Leonardo Citraro, Mateusz Koziński, Pascal Fua

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks.

Overcoming the Domain Gap in Neural Action Representations

no code implementations2 Dec 2021 Semih Günel, Florian Aymanns, Sina Honari, Pavan Ramdya, Pascal Fua

Relating animal behaviors to brain activity is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces.

Dyadic Human Motion Prediction

no code implementations1 Dec 2021 Isinsu Katircioglu, Costa Georgantas, Mathieu Salzmann, Pascal Fua

To evaluate this, and because no existing motion prediction datasets depict two closely-interacting subjects, we introduce the LindyHop600K dance dataset.

Human motion prediction Motion Forecasting +1

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

1 code implementation29 Nov 2021 Benoit Guillard, Federico Stella, Pascal Fua

Unsigned Distance Fields (UDFs) can be used to represent non-watertight surfaces.

Learning to Align Sequential Actions in the Wild

no code implementations17 Nov 2021 Weizhe Liu, Bugra Tekin, Huseyin Coskun, Vibhav Vineet, Pascal Fua, Marc Pollefeys

To this end, we propose an approach to enforce temporal priors on the optimal transport matrix, which leverages temporal consistency, while allowing for variations in the order of actions.

Frame Representation Learning

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

1 code implementation12 Nov 2021 Jan Bednarik, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua

The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible.

Surface Reconstruction

Persistent Homology with Improved Locality Information for more Effective Delineation

no code implementations12 Oct 2021 Doruk Oner, Adélie Garin, Mateusz Koziński, Kathryn Hess, Pascal Fua

We present a new, more effective way to use Persistent Homology (PH), a method to compare the topology of two data sets, for training deep networks to delineate road networks in aerial images and neuronal processes in microscopy scans.

Localized Persistent Homologies for more Effective Deep Learning

no code implementations29 Sep 2021 Doruk Oner, Adélie Garin, Mateusz Kozinski, Kathryn Hess, Pascal Fua

Persistent Homologies have been successfully used to increase the performance of deep networks trained to detect curvilinear structures and to improve the topological quality of the results.

DEBOSH: Deep Bayesian Shape Optimization

no code implementations28 Sep 2021 Nikita Durasov, Artem Lukoyanov, Jonathan Donier, Pascal Fua

Shape optimization is at the heart of many industrial applications, such as aerodynamics, heat transfer, and structural analysis.

HybridSDF: Combining Free Form Shapes and Geometric Primitives for effective Shape Manipulation

no code implementations22 Sep 2021 Subeesh Vasu, Nicolas Talabot, Artem Lukoianov, Pierre Baque, Jonathan Donier, Pascal Fua

CAD modeling typically involves the use of simple geometric primitives whereas recent advances in deep-learning based 3D surface modeling have opened new shape design avenues.

DeepMesh: Differentiable Iso-Surface Extraction

no code implementations20 Jun 2021 Benoit Guillard, Edoardo Remelli, Artem Lukoianov, Stephan R. Richter, Timur Bagautdinov, Pierre Baque, Pascal Fua

Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field.

3D Reconstruction Single-View 3D Reconstruction

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

2 code implementations30 Apr 2021 Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart, Pascal Fua, Mathieu Salzmann, Matthias Rottmann

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes.

Instance Segmentation Semantic Segmentation

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

1 code implementation ICCV 2021 Jan Bednarik, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua, Noam Aigerman

We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes.

Surface Reconstruction

Robust Differentiable SVD

2 code implementations8 Apr 2021 Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.

Image Classification Style Transfer

Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

no code implementations ICCV 2021 Benoit Guillard, Edoardo Remelli, Pierre Yvernay, Pascal Fua

Reconstructing 3D shape from 2D sketches has long been an open problem because the sketches only provide very sparse and ambiguous information.

Translation

Leveraging Self-Supervision for Cross-Domain Crowd Counting

no code implementations30 Mar 2021 Weizhe Liu, Nikita Durasov, Pascal Fua

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density.

Crowd Counting

Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo

1 code implementation22 Mar 2021 David Honzátko, Engin Türetken, Pascal Fua, L. Andrea Dunbar

The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision.

Detecting Road Obstacles by Erasing Them

no code implementations25 Dec 2020 Krzysztof Lis, Sina Honari, Pascal Fua, Mathieu Salzmann

Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector.

Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction

no code implementations21 Dec 2020 Mengshi Qi, Edoardo Remelli, Mathieu Salzmann, Pascal Fua

Deep learning-solutions for hand-object 3D pose and shape estimation are now very effective when an annotated dataset is available to train them to handle the scenarios and lighting conditions they will encounter at test time.

Unsupervised Domain Adaptation

Masksembles for Uncertainty Estimation

1 code implementation CVPR 2021 Nikita Durasov, Timur Bagautdinov, Pierre Baque, Pascal Fua

Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples.

Ensemble Learning Out-of-Distribution Detection +1

Human Detection and Segmentation via Multi-view Consensus

1 code implementation ICCV 2021 Isinsu Katircioglu, Helge Rhodin, Jörg Spörri, Mathieu Salzmann, Pascal Fua

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data.

Human Detection

Long Term Motion Prediction Using Keyposes

1 code implementation8 Dec 2020 Sena Kiciroglu, Wei Wang, Mathieu Salzmann, Pascal Fua

Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving.

Autonomous Driving Human motion prediction +1

Unsupervised Temporal Learning on Monocular Videos for 3D Human Pose Estimation

no code implementations2 Dec 2020 Sina Honari, Victor Constantin, Helge Rhodin, Mathieu Salzmann, Pascal Fua

In this paper we propose an unsupervised learning method to extract temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich latent vectors.

3D Human Pose Estimation Frame

Counting People by Estimating People Flows

1 code implementation1 Dec 2020 Weizhe Liu, Mathieu Salzmann, Pascal Fua

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images.

Active Learning Crowd Counting +1

PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers

1 code implementation CVPR 2021 Frank Yu, Mathieu Salzmann, Pascal Fua, Helge Rhodin

Our conclusion is that it is important to utilize camera calibration information when available, for classical and deep-learning-based computer vision alike.

3D Reconstruction Camera Calibration

A Closed-Form Solution to Local Non-Rigid Structure-from-Motion

no code implementations23 Nov 2020 Shaifali Parashar, Yuxuan Long, Mathieu Salzmann, Pascal Fua

A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express local, differential constraints between pairs of images, from which the surface normal at any point can be obtained by solving a system of polynomial equations.

Deep Active Surface Models

no code implementations CVPR 2021 Udaranga Wickramasinghe, Graham Knott, Pascal Fua

Active Surface Models have a long history of being useful to model complex 3D surfaces but only Active Contours have been used in conjunction with deep networks, and then only to produce the data term as well as meta-parameter maps controlling them.

Surface Reconstruction

Self-supervised Segmentation via Background Inpainting

no code implementations11 Nov 2020 Isinsu Katircioglu, Helge Rhodin, Victor Constantin, Jörg Spörri, Mathieu Salzmann, Pascal Fua

While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on.

Human Detection Object Detection +1

Better Patch Stitching for Parametric Surface Reconstruction

1 code implementation14 Oct 2020 Zhantao Deng, Jan Bednařík, Mathieu Salzmann, Pascal Fua

We introduce an approach that explicitly encourages global consistency of the local mappings.

Surface Reconstruction

Motion Prediction Using Temporal Inception Module

1 code implementation6 Oct 2020 Tim Lebailly, Sena Kiciroglu, Mathieu Salzmann, Pascal Fua, Wei Wang

We argue that the diverse temporal scales are important as they allow us to look at the past frames with different receptive fields, which can lead to better predictions.

Autonomous Driving Human motion prediction +1

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

1 code implementation15 Sep 2020 Doruk Oner, Mateusz Koziński, Leonardo Citraro, Nathan C. Dadap, Alexandra G. Konings, Pascal Fua

The main idea behind our loss is to express the connectivity of roads, or canals, in terms of disconnections that they create between background regions of the image.

GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

no code implementations20 Jul 2020 Erhan Gundogdu, Victor Constantin, Shaifali Parashar, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua

We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the body and garment shapes.

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

no code implementations ECCV 2020 Subeesh Vasu, Mateusz Kozinski, Leonardo Citraro, Pascal Fua

Instead, we use a more sophisticated discriminator that returns a label pyramid describing what portions of the road network are correct at several different scales.

DISK: Learning local features with policy gradient

1 code implementation NeurIPS 2020 Michał J. Tyszkiewicz, Pascal Fua, Eduard Trulls

Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints.

Ranked #3 on Image Matching on IMC PhotoTourism (using extra training data)

Image Matching reinforcement-learning

MeshSDF: Differentiable Iso-Surface Extraction

1 code implementation NeurIPS 2020 Edoardo Remelli, Artem Lukoianov, Stephan R. Richter, Benoît Guillard, Timur Bagautdinov, Pierre Baque, Pascal Fua

Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field.

UCLID-Net: Single View Reconstruction in Object Space

no code implementations NeurIPS 2020 Benoit Guillard, Edoardo Remelli, Pascal Fua

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations.

Domain Adaptive Multibranch Networks

no code implementations ICLR 2020 Róger Bermúdez-Chacón, Mathieu Salzmann, Pascal Fua

We tackle unsupervised domain adaptation by accounting for the fact that different domains may need to be processed differently to arrive to a common feature representation effective for recognition.

Unsupervised Domain Adaptation

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

no code implementations15 Apr 2020 Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann

In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.

Denoising Pose Estimation

Real-Time Camera Pose Estimation for Sports Fields

no code implementations31 Mar 2020 Leonardo Citraro, Pablo Márquez-Neila, Stefano Savarè, Vivek Jayaram, Charles Dubout, Félix Renaut, Andrés Hasfura, Horesh Ben Shitrit, Pascal Fua

Given an image sequence featuring a portion of a sports field filmed by a moving and uncalibrated camera, such as the one of the smartphones, our goal is to compute automatically in real time the focal length and extrinsic camera parameters for each image in the sequence without using a priori knowledges of the position and orientation of the camera.

Pose Estimation

Image Matching across Wide Baselines: From Paper to Practice

5 code implementations3 Mar 2020 Yuhe Jin, Dmytro Mishkin, Anastasiia Mishchuk, Jiri Matas, Pascal Fua, Kwang Moo Yi, Eduard Trulls

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric.

Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals

no code implementations CVPR 2020 Siyuan Li, Semih Günel, Mirela Ostrek, Pavan Ramdya, Pascal Fua, Helge Rhodin

We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models.

Pose Estimation Translation

Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data

1 code implementation8 Dec 2019 Udaranga Wickramasinghe, Edoardo Remelli, Graham Knott, Pascal Fua

CNN-based volumetric methods that label individual voxels now dominate the field of biomedical segmentation.

Towards Reliable Evaluation of Road Network Reconstructions

no code implementations28 Nov 2019 Leonardo Citraro, Mateusz Koziński, Pascal Fua

Existing performance measures rank delineation algorithms inconsistently, which makes it difficult to decide which one is best in any given situation.

Using Depth for Pixel-Wise Detection of Adversarial Attacks in Crowd Counting

no code implementations26 Nov 2019 Weizhe Liu, Mathieu Salzmann, Pascal Fua

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density.

Crowd Counting Density Estimation

Estimating People Flows to Better Count Them in Crowded Scenes

1 code implementation ECCV 2020 Weizhe Liu, Mathieu Salzmann, Pascal Fua

In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing.

Optical Flow Estimation

Shape Reconstruction by Learning Differentiable Surface Representations

1 code implementation CVPR 2020 Jan Bednarik, Shaifali Parashar, Erhan Gundogdu, Mathieu Salzmann, Pascal Fua

Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations.

Single-Stage 6D Object Pose Estimation

1 code implementation CVPR 2020 Yinlin Hu, Pascal Fua, Wei Wang, Mathieu Salzmann

Second, training the deep network relies on a surrogate loss that does not directly reflect the final 6D pose estimation task.

6D Pose Estimation 6D Pose Estimation using RGB

Probabilistic Atlases to Enforce Topological Constraints

1 code implementation18 Sep 2019 Udaranga Wickramasinghe, Graham Knott, Pascal Fua

Probabilistic atlases (PAs) have long been used in standard segmentation approaches and, more recently, in conjunction with Convolutional Neural Networks (CNNs).

Gravity as a Reference for Estimating a Person's Height from Video

no code implementations ICCV 2019 Didier Bieler, Semih Günel, Pascal Fua, Helge Rhodin

We show theoretically and empirically that a simple motion trajectory analysis suffices to translate from pixel measurements to the person's metric height, reaching a MAE of up to 3. 9 cm on jumping motions, and that this works without camera and ground plane calibration.

Motion Capture from Pan-Tilt Cameras with Unknown Orientation

no code implementations30 Aug 2019 Roman Bachmann, Jörg Spörri, Pascal Fua, Helge Rhodin

We propose a method for estimating an athlete's global 3D position and articulated pose using multiple cameras.

Markerless Motion Capture

Beyond Cartesian Representations for Local Descriptors

1 code implementation ICCV 2019 Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi, Pascal Fua, Eduard Trulls

We demonstrate that this representation is particularly amenable to learning descriptors with deep networks.

Self-supervised Training of Proposal-based Segmentation via Background Prediction

no code implementations18 Jul 2019 Isinsu Katircioglu, Helge Rhodin, Victor Constantin, Jörg Spörri, Mathieu Salzmann, Pascal Fua

While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on.

Object Detection

XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera

4 code implementations1 Jul 2019 Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Mohamed Elgharib, Pascal Fua, Hans-Peter Seidel, Helge Rhodin, Gerard Pons-Moll, Christian Theobalt

The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy.

Monocular 3D Human Pose Estimation

Recurrent U-Net for Resource-Constrained Segmentation

no code implementations ICCV 2019 Wei Wang, Kaicheng Yu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann

State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs.

Hand Segmentation

Detecting the Unexpected via Image Resynthesis

3 code implementations ICCV 2019 Krzysztof Lis, Krishna Nakka, Pascal Fua, Mathieu Salzmann

In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time.

Resynthesis Semantic Segmentation

Neural Scene Decomposition for Multi-Person Motion Capture

1 code implementation CVPR 2019 Helge Rhodin, Victor Constantin, Isinsu Katircioglu, Mathieu Salzmann, Pascal Fua

To this end, we introduce a self-supervised approach to learning what we call a neural scene decomposition (NSD) that can be exploited for 3D pose estimation.

3D Pose Estimation Frame +2

NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler

no code implementations27 Jan 2019 Edoardo Remelli, Pierre Baque, Pascal Fua

Most algorithms that rely on deep learning-based approaches to generate 3D point sets can only produce clouds containing fixed number of points.

Segmentation-driven 6D Object Pose Estimation

5 code implementations CVPR 2019 Yinlin Hu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm.

6D Pose Estimation 6D Pose Estimation using RGB +1

Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation

no code implementations27 Nov 2018 Wei Wang, Kaicheng Yu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann

As evidenced by our results on standard hand segmentation benchmarks and on our own dataset, our approach outperforms these other, simpler recurrent segmentation techniques, as well as the state-of-the-art hand segmentation one.

Hand Segmentation Mixed Reality

Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking

no code implementations27 Nov 2018 Andrii Maksai, Pascal Fua

Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with.

Multiple Object Tracking

Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation

1 code implementation26 Nov 2018 Mateusz Koziński, Agata Mosinska, Mathieu Salzmann, Pascal Fua

The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis.

Context-Aware Crowd Counting

1 code implementation CVPR 2019 Weizhe Liu, Mathieu Salzmann, Pascal Fua

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density.

Crowd Counting

Modeling Facial Geometry Using Compositional VAEs

no code implementations CVPR 2018 Timur Bagautdinov, Chenglei Wu, Jason Saragih, Pascal Fua, Yaser Sheikh

We propose a method for learning non-linear face geometry representations using deep generative models.

What Face and Body Shapes Can Tell About Height

no code implementations25 May 2018 Semih Günel, Helge Rhodin, Pascal Fua

Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance, however, it is also very challenging due to the absence of absolute scale information.

Autonomous Driving Face Recognition

LF-Net: Learning Local Features from Images

3 code implementations NeurIPS 2018 Yuki Ono, Eduard Trulls, Pascal Fua, Kwang Moo Yi

We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision.

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

1 code implementation23 Mar 2018 Jan Bednařík, Pascal Fua, Mathieu Salzmann

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured.

3D Reconstruction

Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses

no code implementations ECCV 2018 Zheng Dang, Kwang Moo Yi, Yinlin Hu, Fei Wang, Pascal Fua, Mathieu Salzmann

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system.

3D Pose Estimation

Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera

no code implementations15 Mar 2018 Weipeng Xu, Avishek Chatterjee, Michael Zollhoefer, Helge Rhodin, Pascal Fua, Hans-Peter Seidel, Christian Theobalt

We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera.

3D Pose Estimation

Beyond the Pixel-Wise Loss for Topology-Aware Delineation

no code implementations CVPR 2018 Agata Mosinska, Pablo Marquez-Neila, Mateusz Kozinski, Pascal Fua

We propose a new loss term that is aware of the higher-order topological features of linear structures.

Real-Time Seamless Single Shot 6D Object Pose Prediction

6 code implementations CVPR 2018 Bugra Tekin, Sudipta N. Sinha, Pascal Fua

For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent CNN-based approaches when they are all used without post-processing.

6D Pose Estimation using RGB Drone Pose Estimation +1

Residual Parameter Transfer for Deep Domain Adaptation

no code implementations CVPR 2018 Artem Rozantsev, Mathieu Salzmann, Pascal Fua

The goal of Deep Domain Adaptation is to make it possible to use Deep Nets trained in one domain where there is enough annotated training data in another where there is little or none.

Domain Adaptation

Learning to Find Good Correspondences

3 code implementations CVPR 2018 Kwang Moo Yi, Eduard Trulls, Yuki Ono, Vincent Lepetit, Mathieu Salzmann, Pascal Fua

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo.

Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery

1 code implementation18 Oct 2017 Thomas Kurmann, Pablo Marquez Neila, Xiaofei Du, Pascal Fua, Danail Stoyanov, Sebastian Wolf, Raphael Sznitman

An additional advantage of our approach is that instrument detection at test time is achieved while avoiding the need for scale-dependent sliding window evaluation.

Pose Estimation

Non-Markovian Globally Consistent Multi-Object Tracking

no code implementations ICCV 2017 Andrii Maksai, Xinchao Wang, Francois Fleuret, Pascal Fua

Many state-of-the-art approaches to multi-object tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories.

Frame Multi-Object Tracking

Imposing Hard Constraints on Deep Networks: Promises and Limitations

no code implementations7 Jun 2017 Pablo Márquez-Neila, Mathieu Salzmann, Pascal Fua

Imposing constraints on the output of a Deep Neural Net is one way to improve the quality of its predictions while loosening the requirements for labeled training data.

Active Learning and Proofreading for Delineation of Curvilinear Structures

no code implementations23 Dec 2016 Agata Mosinska, Jakub Tarnawski, Pascal Fua

In a proofreading context, we similarly find regions of the resulting reconstruction that should be verified in priority to obtain a nearly-perfect result.

Active Learning General Classification

Globally Consistent Multi-People Tracking using Motion Patterns

1 code implementation2 Dec 2016 Andrii Maksai, Xinchao Wang, Francois Fleuret, Pascal Fua

Many state-of-the-art approaches to people tracking rely on detecting them in each frame independently, grouping detections into short but reliable trajectory segments, and then further grouping them into full trajectories.

Frame

Flight Dynamics-based Recovery of a UAV Trajectory using Ground Cameras

no code implementations CVPR 2017 Artem Rozantsev, Sudipta N. Sinha, Debadeepta Dey, Pascal Fua

Our main contribution is a new bundle adjustment procedure which in addition to optimizing the camera poses, regularizes the point trajectory using a prior based on motion dynamics (or specifically flight dynamics).

3D Reconstruction Frame

Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision

no code implementations29 Nov 2016 Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal Fua, Oleksandr Sotnychenko, Weipeng Xu, Christian Theobalt

We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data.

Monocular 3D Human Pose Estimation Transfer Learning

Uniform Information Segmentation

no code implementations27 Nov 2016 Radhakrishna Achanta, Pablo Márquez-Neila, Pascal Fua, Sabine Süsstrunk

Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details.

Superpixels

Geometry in Active Learning for Binary and Multi-class Image Segmentation

no code implementations29 Jun 2016 Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

Our approach combines geometric smoothness priors in the image space with more traditional uncertainty measures to estimate which pixels or voxels are the most informative, and thus should to be annotated next.

Active Learning Semantic Segmentation

Learning to Match Aerial Images With Deep Attentive Architectures

no code implementations CVPR 2016 Hani Altwaijry, Eduard Trulls, James Hays, Pascal Fua, Serge Belongie

We demonstrate that our models outperform the state-of-the-art on ultra-wide baseline matching and approach human accuracy.

LIFT: Learned Invariant Feature Transform

1 code implementation30 Mar 2016 Kwang Moo Yi, Eduard Trulls, Vincent Lepetit, Pascal Fua

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description.

Beyond Sharing Weights for Deep Domain Adaptation

no code implementations21 Mar 2016 Artem Rozantsev, Mathieu Salzmann, Pascal Fua

To this end, we introduce a two-stream architecture, where one operates in the source domain and the other in the target domain.

Domain Adaptation Object Recognition

Do We Need Binary Features for 3D Reconstruction?

no code implementations14 Feb 2016 Bin Fan, Qingqun Kong, Wei Sui, Zhiheng Wang, Xinchao Wang, Shiming Xiang, Chunhong Pan, Pascal Fua

Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.

3D Reconstruction

Active Learning for Delineation of Curvilinear Structures

no code implementations CVPR 2016 Agata Mosinska, Raphael Sznitman, Przemysław Głowacki, Pascal Fua

Many recent delineation techniques owe much of their increased effectiveness to path classification algorithms that make it possible to distinguish promising paths from others.

Active Learning General Classification

Kullback-Leibler Proximal Variational Inference

no code implementations NeurIPS 2015 Mohammad E. Khan, Pierre Baque, François Fleuret, Pascal Fua

Secondly, we use the proximal framework to derive efficient variational algorithms for non-conjugate models.

Variational Inference

Hot or Not: Exploring Correlations Between Appearance and Temperature

no code implementations ICCV 2015 Daniel Glasner, Pascal Fua, Todd Zickler, Lihi Zelnik-Manor

In this paper we explore interactions between the appearance of an outdoor scene and the ambient temperature.

Discriminative Learning of Deep Convolutional Feature Point Descriptors

1 code implementation ICCV 2015 Edgar Simo-Serra, Eduard Trulls, Luis Ferraz, Iasonas Kokkinos, Pascal Fua, Francesc Moreno-Noguer

Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e. g. SIFT.

Satellite Image Classification

Projection Onto the Manifold of Elongated Structures for Accurate Extraction

no code implementations ICCV 2015 Amos Sironi, Vincent Lepetit, Pascal Fua

Detection of elongated structures in 2D images and 3D image stacks is a critical prerequisite in many applications and Machine Learning-based approaches have recently been shown to deliver superior performance.

Direct Prediction of 3D Body Poses from Motion Compensated Sequences

no code implementations CVPR 2016 Bugra Tekin, Artem Rozantsev, Vincent Lepetit, Pascal Fua

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people.

3D Human Pose Estimation Frame

Learning to Assign Orientations to Feature Points

no code implementations CVPR 2016 Kwang Moo Yi, Yannick Verdie, Pascal Fua, Vincent Lepetit

We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point.

Introducing Geometry in Active Learning for Image Segmentation

no code implementations ICCV 2015 Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes.

Active Learning Semantic Segmentation

Probability Occupancy Maps for Occluded Depth Images

no code implementations CVPR 2015 Timur Bagautdinov, Francois Fleuret, Pascal Fua

We propose a novel approach to computing the probabilities of presence of multiple and potentially occluding objects in a scene from a single depth map.

Predicting People's 3D Poses from Short Sequences

no code implementations30 Apr 2015 Bugra Tekin, Xiaolu Sun, Xinchao Wang, Vincent Lepetit, Pascal Fua

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people.

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

no code implementations16 Mar 2015 Dat Tien Ngo, Jonas Ostlund, Pascal Fua

We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem.

3D Shape Reconstruction Surface Reconstruction

Dense image registration and deformable surface reconstruction in presence of occlusions and minimal texture

no code implementations ICCV 2015 Dat Tien Ngo, Sanghuyk Park, Anne Jorstad, Alberto Crivellaro, Chang Yoo, Pascal Fua

In this work, we explicitly address the problem of 3D reconstruction of poorly textured, occluded surfaces, proposing a framework based on a template-matching approach that scales dense robust features by a relevancy score.

3D Reconstruction Image Registration +2

A provably convergent alternating minimization method for mean field inference

no code implementations20 Feb 2015 Pierre Baqué, Jean-Hubert Hours, François Fleuret, Pascal Fua

Mean-Field is an efficient way to approximate a posterior distribution in complex graphical models and constitutes the most popular class of Bayesian variational approximation methods.

Modeling Brain Circuitry over a Wide Range of Scales

no code implementations13 Feb 2015 Pascal Fua, Graham Knott

If we are ever to unravel the mysteries of brain function at its most fundamental level, we will need a precise understanding of how its component neurons connect to each other.

Globally Optimal Cell Tracking using Integer Programming

no code implementations22 Jan 2015 Engin Türetken, Xinchao Wang, Carlos Becker, Carsten Haubold, Pascal Fua

We propose a novel approach to automatically tracking cell populations in time-lapse images.

On Rendering Synthetic Images for Training an Object Detector

no code implementations28 Nov 2014 Artem Rozantsev, Vincent Lepetit, Pascal Fua

We propose a novel approach to synthesizing images that are effective for training object detectors.

Flying Objects Detection from a Single Moving Camera

no code implementations CVPR 2015 Artem Rozantsev, Vincent Lepetit, Pascal Fua

We propose an approach to detect flying objects such as UAVs and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves.

General Classification

TILDE: A Temporally Invariant Learned DEtector

no code implementations CVPR 2015 Yannick Verdie, Kwang Moo Yi, Pascal Fua, Vincent Lepetit

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive.

Multiple human pose estimation with temporally consistent 3d pictorial structures

no code implementations6 Sep 2014 Vasileios Belagiannis, Xinchao Wang, Bernt Schiele, Pascal Fua, Slobodan Ilic, Nassir Navab

To address these challenges, we propose a temporally consistent 3D Pictorial Structures model (3DPS) for multiple human pose estimation from multiple camera views.

3D Multi-Person Pose Estimation 3D Pose Estimation

Beyond KernelBoost

no code implementations28 Jul 2014 Roberto Rigamonti, Vincent Lepetit, Pascal Fua

In this Technical Report we propose a set of improvements with respect to the KernelBoost classifier presented in [Becker et al., MICCAI 2013].

Reconstructing Evolving Tree Structures in Time Lapse Sequences

no code implementations CVPR 2014 Przemyslaw Glowacki, Miguel Amavel Pinheiro, Engin Turetken, Raphael Sznitman, Daniel Lebrecht, Jan Kybic, Anthony Holtmaat, Pascal Fua

We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches.

Multiscale Centerline Detection by Learning a Scale-Space Distance Transform

no code implementations CVPR 2014 Amos Sironi, Vincent Lepetit, Pascal Fua

We propose a robust and accurate method to extract the centerlines and scale of tubular structures in 2D images and 3D volumes.

Non-Linear Domain Adaptation with Boosting

no code implementations NeurIPS 2013 Carlos J. Becker, Christos M. Christoudias, Pascal Fua

This problem is accentuated with 3D data, for which annotation is very time-consuming, limiting the amount of data that can be labeled in new acquisitions for training.

Domain Adaptation Multi-Task Learning

Boosting Binary Keypoint Descriptors

no code implementations CVPR 2013 Tomasz Trzcinski, Mario Christoudias, Pascal Fua, Vincent Lepetit

Binary keypoint descriptors provide an efficient alternative to their floating-point competitors as they enable faster processing while requiring less memory.

Reconstructing Loopy Curvilinear Structures Using Integer Programming

no code implementations CVPR 2013 Engin Turetken, Fethallah Benmansour, Bjoern Andres, Hanspeter Pfister, Pascal Fua

We propose a novel approach to automated delineation of linear structures that form complex and potentially loopy networks.

Fast Object Detection with Entropy-Driven Evaluation

no code implementations CVPR 2013 Raphael Sznitman, Carlos Becker, Francois Fleuret, Pascal Fua

Cascade-style approaches to implementing ensemble classifiers can deliver significant speed-ups at test time.

Real-Time Object Detection

Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets

no code implementations CVPR 2013 Aurelien Lucchi, Yunpeng Li, Pascal Fua

We propose a working set based approximate subgradient descent algorithm to minimize the margin-sensitive hinge loss arising from the soft constraints in max-margin learning frameworks, such as the structured SVM.

Semantic Segmentation Structured Prediction

Learning Separable Filters

no code implementations CVPR 2013 Roberto Rigamonti, Amos Sironi, Vincent Lepetit, Pascal Fua

Learning filters to produce sparse image representations in terms of overcomplete dictionaries has emerged as a powerful way to create image features for many different purposes.

Deriving And Combining Continuous Possibility Functions in the Framework of Evidential Reasoning

no code implementations27 Mar 2013 Pascal Fua

We discuss the relationship between Dempster's rule and our proposed rule for combining evidence over continuous frames.

Learning Image Descriptors with the Boosting-Trick

no code implementations NeurIPS 2012 Tomasz Trzcinski, Mario Christoudias, Vincent Lepetit, Pascal Fua

The main goal of local feature descriptors is to distinctively represent a salient image region while remaining invariant to viewpoint and illumination changes.

Object Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.