Search Results for author:
Found 59 papers, 31 papers with code
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation
Monocular 3D human pose and shape estimation is an ill-posed problem since multiple 3D solutions can explain a 2D image of a subject.
Ranked #51 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
IMP: Iterative Matching and Pose Estimation with Adaptive Pooling
Previous methods solve feature matching and pose estimation using a two-stage process by first finding matches and then estimating the pose.
SFD2: Semantic-guided Feature Detection and Description
Visual localization is a fundamental task for various applications including autonomous driving and robotics.
FIND: An Unsupervised Implicit 3D Model of Articulated Human Feet
In this paper we present a high fidelity and articulated 3D human foot model.
Model-Based Imitation Learning for Urban Driving
Our approach is the first camera-only method that models static scene, dynamic scene, and ego-behaviour in an urban driving environment.
A CNN Based Approach for the Point-Light Photometric Stereo Problem
Reconstructing the 3D shape of an object using several images under different light sources is a very challenging task, especially when realistic assumptions such as light propagation and attenuation, perspective viewing geometry and specular light reflection are considered.
IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty
The depth of each pixel can be propagated to a query pixel, using the predicted surface normal as guidance.
Ranked #23 on
Monocular Depth Estimation
on NYU-Depth V2
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Such models are trained on large-scale datasets that contain millions of real human face images collected from the internet.
Ranked #1 on
Face Recognition
on AgeDB
SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image
This combined information is the input to a pose prediction network, SPARC-Net which we train to predict a 9 DoF CAD model pose update.
Contrastive Unsupervised Learning of World Model with Invariant Causal Features
In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across augmentations of irrelevant parts or styles of the observation.
Efficient Large-Scale Localization by Global Instance Recognition
Hierarchical frameworks consisting of both coarse and fine localization are often used as the standard pipeline for large-scale visual localization.
Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
To this end, we propose MaGNet, a novel framework for fusing single-view depth probability with multi-view geometry, to improve the accuracy, robustness and efficiency of multi-view depth estimation.
Discrete neural representations for explainable anomaly detection
The aim of this work is to detect and automatically generate high-level explanations of anomalous events in video.
Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model
This paper addresses the problem of 3D human body shape and pose estimation from RGB images.
Leveraging Geometry for Shape Estimation from a Single RGB Image
In this work we demonstrate how cross-domain keypoint matches from an RGB image to a rendered CAD model allow for more precise object pose predictions compared to ones obtained through direct predictions.
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild
Thus, it is desirable to estimate a distribution over 3D body shape and pose conditioned on the input image instead of a single 3D reconstruction.
Ranked #1 on
3D Human Shape Estimation
on SSP-3D
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation
Experimental results show that the proposed method outperforms the state-of-the-art in ScanNet and NYUv2, and that the estimated uncertainty correlates well with the prediction error.
Ranked #1 on
Surface Normals Estimation
on ScanNetV2
X-MAN: Explaining multiple sources of anomalies in video
In an effort to tackle this problem we make the following contributions: (1) we show how to build interpretable feature representations suitable for detecting anomalies with state of the art performance, (2) we propose an interpretable probabilistic anomaly detector which can describe the reason behind it's response using high level concepts, (3) we are the first to directly consider object interactions for anomaly detection and (4) we propose a new task of explaining anomalies and release a large dataset for evaluating methods on this task.
LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
In order to fill the gap in evaluating near-field photometric stereo methods, we introduce LUCES the first real-world 'dataset for near-fieLd point light soUrCe photomEtric Stereo' of 14 objects of a varying of materials.
FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
We present FIERY: a probabilistic future prediction model in bird's-eye view from monocular cameras.
Ranked #1 on
Bird's-Eye View Semantic Segmentation
on nuScenes
Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
In contrast, we propose a new task: shape and pose estimation from a group of multiple images of a human subject, without constraints on subject pose, camera viewpoint or background conditions between images in the group.
Ranked #3 on
3D Human Shape Estimation
on SSP-3D
Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild
Thus, we propose STRAPS (Synthetic Training for Real Accurate Pose and Shape), a system that utilises proxy representations, such as silhouettes and 2D joints, as inputs to a shape and pose regression neural network, which is trained with synthetic training data (generated on-the-fly during training using the SMPL statistical body model) to overcome data scarcity.
Ranked #1 on
3D Human Shape Estimation
on MoVi
3D human pose and shape estimation
3D Human Shape Estimation
+3
A CNN Based Approach for the Near-Field Photometric Stereo Problem
Secondly, we compute the depth by integrating the normal field in order to iteratively estimate light directions and attenuation which is used to compensate the input images to compute reflectance samples for the next iteration.
Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments
We present NavACL, a method of automatic curriculum learning tailored to the navigation task.
PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks
We show that global physical effects can be approximated on the observation map domain and this simplifies and speeds up the data creation procedure.
Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
We introduce an automatic, end-to-end method for recovering the 3D pose and shape of dogs from monocular internet images.
Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks
Autonomous vehicles commonly rely on highly detailed birds-eye-view maps of their environment, which capture both static elements of the scene such as road layout as well as dynamic elements such as other cars and pedestrians.
Learning a Spatio-Temporal Embedding for Video Instance Segmentation
We present a novel embedding approach for video instance segmentation.
Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression
We obtain smaller mean distance and angular errors than state-of-the-art 6-DoF pose estimation algorithms based on direct pose regression and pose estimation from scene coordinates on all datasets.
Orientation-aware Semantic Segmentation on Icosahedron Spheres
For the spherical domain, several methods recently adopt an icosahedron mesh, but systems are typically rotation invariant or require significant memory and parameters, thus enabling execution only at very low resolutions.
Ranked #14 on
Semantic Segmentation
on Stanford2D3D Panoramic
Fast-SCNN: Fast Semantic Segmentation Network
The encoder-decoder framework is state-of-the-art for offline semantic image segmentation.
Ranked #7 on
Semantic Segmentation
on SynPASS
Orthographic Feature Transform for Monocular 3D Object Detection
This allows us to reason holistically about the spatial configuration of the scene in a domain where scale is consistent and distances between objects are meaningful.
3D Object Detection From Monocular Images
Monocular 3D Object Detection
+1
Creatures great and SMAL: Recovering the shape and motion of animals from video
We present a system to recover the 3D shape and motion of a wide variety of quadrupeds from video.
A Differential Volumetric Approach to Multi-View Photometric Stereo
In this work, we present a volumetric approach to the multi-view photometric stereo problem.
Convolutional CRFs for Semantic Segmentation
For the challenging semantic image segmentation task the most efficient models have traditionally combined the structured modelling capabilities of Conditional Random Fields (CRFs) with the feature extraction power of CNNs.
Semi-Calibrated Near Field Photometric Stereo
3D reconstruction from shading information through Photometric Stereo is considered a very challenging problem in Computer Vision.
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives.
Geometric Loss Functions for Camera Pose Regression with Deep Learning
Deep learning has shown to be effective for robust and real-time monocular image relocalisation.
MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving
While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving.
Understanding Real World Indoor Scenes With Synthetic Data
Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments.
Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root.
Refining Architectures of Deep Convolutional Neural Networks
Deep Convolutional Neural Networks (CNNs) have recently evinced immense success for various image recognition tasks.
SceneNet: Understanding Real World Indoor Scenes With Synthetic Data
Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments.
Training CNNs with Low-Rank Filters for Efficient Image Classification
Applying our method to a near state-of-the-art network for CIFAR, we achieved comparable accuracy with 46% less compute and 55% fewer parameters.
Spatio-temporal video autoencoder with differentiable memory
At each time step, the system receives as input a video frame, predicts the optical flow based on the current observation and the LSTM memory state as a dense transformation map, and applies it to the current frame to generate the next frame.
TemplateNet for Depth-Based Object Instance Recognition
We present a novel deep architecture termed templateNet for depth based object instance recognition.
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making.
Symmetry-invariant optimization in deep networks
Recent works have highlighted scale invariance or symmetry that is present in the weight space of a typical deep network and the adverse effect that it has on the Euclidean gradient based stochastic gradient descent optimization.
Understanding symmetries in deep networks
Consequently, training the network boils down to using stochastic gradient descent updates on the unit-norm manifold.
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.
Ranked #3 on
Medical Image Segmentation
on RITE
Modelling Uncertainty in Deep Learning for Camera Relocalization
Using a Bayesian convolutional neural network implementation we obtain an estimate of the model's relocalization uncertainty and improve state of the art localization accuracy on a large scale outdoor dataset.
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling
These methods lack a mechanism to map deep layer feature maps to input dimensions.
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
We present a robust and real-time monocular six degree of freedom relocalization system.
SynthCam3D: Semantic Understanding With Synthetic Indoor Scenes
We are interested in automatic scene understanding from geometric cues.
DEEP-CARVING: Discovering Visual Attributes by Carving Deep Neural Nets
To ameliorate this limitation, we propose Deep-Carving, a novel training procedure with CNNs, that helps the net efficiently carve itself for the task of multiple attribute prediction.
Bi-label Propagation for Generic Multiple Object Tracking
In this paper, we propose a label propagation framework to handle the multiple object tracking (MOT) problem for a generic object type (cf.
Expressive Visual Text-to-Speech Using Active Appearance Models
This paper presents a complete system for expressive visual text-to-speech (VTTS), which is capable of producing expressive output, in the form of a 'talking head', given an input text and a set of continuous expression weights.
Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest
This work addresses the challenging problem of unconstrained 3D human pose estimation (HPE) from a novel perspective.
MCBoost: Multiple Classifier Boosting for Perceptual Co-clustering of Images and Visual Features
We present a new co-clustering problem of images and visual features.
