Search Results for author: Vincent Lepetit

Found 102 papers, 40 papers with code

S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching

1 code implementation ECCV 2020 Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms.

Visual Localization

UNIT: Unsupervised Online Instance Segmentation through Time

no code implementations12 Sep 2024 Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit

To that end, we leverage an instance segmentation backbone and propose a new training recipe that enables the online tracking of objects.

Instance Segmentation Segmentation +1

GuidedRec: Guiding Ill-Posed Unsupervised Volumetric Recovery

no code implementations20 May 2024 Alexandre Cafaro, Amaury Leroy, Guillaume Beldjoudi, Pauline Maury, Charlotte Robert, Eric Deutsch, Vincent Grégoire, Vincent Lepetit, Nikos Paragios

Earlier methods that work by deforming this volume to match the projections typically fail when the number of projections is very low as the alignment becomes underconstrained.

PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction

no code implementations16 Apr 2024 Sinisa Stekovic, Stefan Ainetter, Mattia D'Urso, Friedrich Fraundorfer, Vincent Lepetit

In our experiments, we apply our algorithm to reconstruct 3D objects in the ScanNet dataset and evaluate our results against CAD model retrieval-based reconstructions.

3D Reconstruction 3D Shape Reconstruction +2

Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

no code implementations21 Mar 2024 Antoine Guédon, Vincent Lepetit

We propose Gaussian Frosting, a novel mesh-based representation for high-quality rendering and editing of complex 3D effects in real-time.

Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection

no code implementations7 Dec 2023 Kohei Yamashita, Vincent Lepetit, Ko Nishino

In this paper, we introduce correspondences of the third kind we call reflection correspondences and show that they can help estimate camera pose by just looking at objects without relying on the background.

Camera Pose Estimation Motion Estimation +2

SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

2 code implementations CVPR 2024 Antoine Guédon, Vincent Lepetit

It is however challenging to extract a mesh from the millions of tiny 3D gaussians as these gaussians tend to be unorganized after optimization and no method has been proposed so far.

BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds

1 code implementation26 Oct 2023 Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit

We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds.

Semantic Segmentation

HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans

2 code implementations12 Sep 2023 Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We present an automated and efficient approach for retrieving high-quality CAD models of objects and their poses in a scene captured by a moving RGB-D camera.

3D Object Retrieval 3D Scene Reconstruction +3

You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation

1 code implementation ICCV 2023 Nermin Samet, Oriane Siméoni, Gilles Puy, Georgy Ponimatkin, Renaud Marlet, Vincent Lepetit

Assuming that images of the point clouds are available, which is common, our method relies on powerful unsupervised image features to measure the diversity of the point clouds.

3D Semantic Segmentation Active Learning +1

NOPE: Novel Object Pose Estimation from a Single Image

1 code implementation CVPR 2024 Van Nguyen Nguyen, Thibault Groueix, Yinlin Hu, Mathieu Salzmann, Vincent Lepetit

The practicality of 3D object pose estimation remains limited for many applications due to the need for prior knowledge of a 3D model and a training period for new objects.

Object Pose Estimation

MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision

no code implementations CVPR 2023 Antoine Guédon, Tom Monnier, Pascal Monasse, Vincent Lepetit

We introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only.

Automatically Annotating Indoor Images with CAD Models via RGB-D Scans

2 code implementations22 Dec 2022 Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans.

3D Object Retrieval Pose Estimation +1

In-Hand 3D Object Scanning from an RGB Sequence

no code implementations CVPR 2023 Shreyas Hampali, Tomas Hodan, Luan Tran, Lingni Ma, Cem Keskin, Vincent Lepetit

As direct optimization over all shape and pose parameters is prone to fail without coarse-level initialization, we propose an incremental approach that starts by splitting the sequence into carefully selected overlapping segments within which the optimization is likely to succeed.

Object

Long-Lived Accurate Keypoints in Event Streams

no code implementations21 Sep 2022 Philippe Chiberre, Etienne Perot, Amos Sironi, Vincent Lepetit

Since this integration is required, we claim it is better to predict the keypoints' trajectories for the time period rather than single locations, as done in previous approaches.

Keypoint Detection

PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking

1 code implementation15 Sep 2022 Van Nguyen Nguyen, Yuming Du, Yang Xiao, Michael Ramamonjisoa, Vincent Lepetit

Our results on challenging datasets are on par with previous works that require much more information (training images of the target objects, 3D models, and/or depth data).

3D geometry

SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration

1 code implementation22 Aug 2022 Antoine Guédon, Pascal Monasse, Vincent Lepetit

Our method scales to large scenes and handles free camera motion: It takes as input an arbitrarily large point cloud gathered by a depth sensor as well as camera poses to predict NBV.

MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

1 code implementation28 Jul 2022 Michaël Ramamonjisoa, Sinisa Stekovic, Vincent Lepetit

We present MonteBoxFinder, a method that, given a noisy input point cloud, fits cuboids to the input scene.

Scene Understanding

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

2 code implementations CVPR 2022 Van Nguyen Nguyen, Yinlin Hu, Yang Xiao, Mathieu Salzmann, Vincent Lepetit

It relies on a small set of training objects to learn local object representations, which allow us to locally match the input image to a set of "templates", rendered images of the CAD models for the new objects.

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

UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution

2 code implementations22 Oct 2021 Yuming Du, Wen Guo, Yang Xiao, Vincent Lepetit

In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method.

Instance Segmentation Optical Flow Estimation +3

HO-3D_v3: Improving the Accuracy of Hand-Object Annotations of the HO-3D Dataset

1 code implementation2 Jul 2021 Shreyas Hampali, Sayan Deb Sarkar, Vincent Lepetit

HO-3D is a dataset providing image sequences of various hand-object interaction scenarios annotated with the 3D pose of the hand and the object and was originally introduced as HO-3D_v2.

Object

Visual Correspondence Hallucination

no code implementations ICLR 2022 Hugo Germain, Vincent Lepetit, Guillaume Bourmaud

Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded or outside the field of view.

Camera Pose Estimation Hallucination +1

Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos

no code implementations ICCV 2021 Yuming Du, Yang Xiao, Vincent Lepetit

Through extensive experiments, we show that our method can generate a high-quality training set which significantly boosts the performance of segmenting objects of unseen classes.

Object Open-World Instance Segmentation +3

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans

2 code implementations ICCV 2021 Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer, Vincent Lepetit

For this step, we propose a novel differentiable method for rendering the polygonal shapes of these proposals.

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose

2 code implementations CVPR 2021 Paul-Edouard Sarlin, Ajaykumar Unagar, Måns Larsson, Hugo Germain, Carl Toft, Viktor Larsson, Marc Pollefeys, Vincent Lepetit, Lars Hammarstrand, Fredrik Kahl, Torsten Sattler

In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms.

3D geometry Camera Localization +3

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

1 code implementation CVPR 2021 Hugo Germain, Vincent Lepetit, Guillaume Bourmaud

Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point problem that minimizes, with respect to the camera pose, the sum of so-called Reprojection Errors (RE).

3D geometry Camera Pose Estimation +1

3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

no code implementations8 Oct 2020 Giorgia Pitteri, Aurélie Bugeau, Slobodan Ilic, Vincent Lepetit

We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects.

3D geometry 3D Object Detection +2

Recent Advances in 3D Object and Hand Pose Estimation

no code implementations10 Jun 2020 Vincent Lepetit

3D object and hand pose estimation have huge potentials for Augmented Reality, to enable tangible interfaces, natural interfaces, and blurring the boundaries between the real and virtual worlds.

Hand Pose Estimation Object

ALCN: Adaptive Local Contrast Normalization

no code implementations15 Apr 2020 Mahdi Rad, Peter M. Roth, Vincent Lepetit

We show that our method significantly outperforms standard normalization methods and would also be appear to be universal since it does not have to be re-trained for each new application.

3D Object Detection Face Recognition +1

S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching

2 code implementations3 Apr 2020 Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms.

Visual Localization

Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields

2 code implementations CVPR 2020 Michael Ramamonjisoa, Yuming Du, Vincent Lepetit

Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours for the occlusion boundaries in the input image.

Monocular Depth Estimation

General 3D Room Layout from a Single View by Render-and-Compare

1 code implementation ECCV 2020 Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit

In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate.

Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation

no code implementations27 Oct 2019 Martin Hirzer, Peter M. Roth, Vincent Lepetit

We propose a novel method to efficiently estimate the spatial layout of a room from a single monocular RGB image.

Room Layout Estimation Segmentation +1

CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining

no code implementations29 Aug 2019 Giorgia Pitteri, Slobodan Ilic, Vincent Lepetit

We first learn to detect object corners of various shapes in images and also to predict their 3D poses, by using training images of a small set of objects.

3D geometry 3D Pose Estimation +1

On Object Symmetries and 6D Pose Estimation from Images

no code implementations20 Aug 2019 Giorgia Pitteri, Michaël Ramamonjisoa, Slobodan Ilic, Vincent Lepetit

Objects with symmetries are common in our daily life and in industrial contexts, but are often ignored in the recent literature on 6D pose estimation from images.

6D Pose Estimation Object

Location Field Descriptors: Single Image 3D Model Retrieval in the Wild

no code implementations7 Aug 2019 Alexander Grabner, Peter M. Roth, Vincent Lepetit

We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild.

Retrieval

Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localization

1 code implementation9 Jul 2019 Hugo Germain, Guillaume Bourmaud, Vincent Lepetit

Given a query image, we first match it against a database of registered reference images, using recent retrieval techniques.

Retrieval Visual Localization

AssemblyNet: A Novel Deep Decision-Making Process for Whole Brain MRI Segmentation

no code implementations5 Jun 2019 Pierrick Coupé, Boris Mansencal, Michaël Clément, Rémi Giraud, Baudouin Denis de Senneville, Vinh-Thong Ta, Vincent Lepetit, José V. Manjon

Whole brain segmentation using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images.

Brain Segmentation Decision Making +1

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

1 code implementation21 May 2019 Michaël Ramamonjisoa, Vincent Lepetit

We demonstrate our approach on the challenging NYUv2-Depth dataset, and show that our method outperforms the state-of-the-art along occluding contours, while performing on par with the best recent methods for the rest of the images.

Depth Prediction Monocular Depth Estimation +2

Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning

no code implementations29 Apr 2019 Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-of-the-art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not part of the dataset, because of the dataset bias, a common phenomenon in computer vision.

Semantic Segmentation

Generalized Feedback Loop for Joint Hand-Object Pose Estimation

no code implementations25 Mar 2019 Markus Oberweger, Paul Wohlhart, Vincent Lepetit

We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop.

hand-object pose Object

S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation

no code implementations27 Dec 2018 Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views.

Segmentation Semi-Supervised Semantic Segmentation

Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation

no code implementations ECCV 2018 Markus Oberweger, Mahdi Rad, Vincent Lepetit

We introduce a novel method for robust and accurate 3D object pose estimation from a single color image under large occlusions.

Object Pose Estimation

Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images

no code implementations CVPR 2018 Mahdi Rad, Markus Oberweger, Vincent Lepetit

The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy to create a virtually infinite training set made of such images, while capturing and annotating real images can be very cumbersome.

3D Hand Pose Estimation

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.

Going Further with Point Pair Features

no code implementations11 Nov 2017 Stefan Hinterstoisser, Vincent Lepetit, Naresh Rajkumar, Kurt Konolige

Point Pair Features is a widely used method to detect 3D objects in point clouds, however they are prone to fail in presence of sensor noise and background clutter.

6D Pose Estimation using RGB

On Pre-Trained Image Features and Synthetic Images for Deep Learning

no code implementations29 Oct 2017 Stefan Hinterstoisser, Vincent Lepetit, Paul Wohlhart, Kurt Konolige

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling.

Object Object Recognition

ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation

no code implementations31 Aug 2017 Mahdi Rad, Peter M. Roth, Vincent Lepetit

We therefore propose a novel illumination normalization method that lets us learn to detect objects and estimate their 3D pose under challenging illumination conditions from very few training samples.

3D Pose Estimation Meta-Learning

DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation

4 code implementations28 Aug 2017 Markus Oberweger, Vincent Lepetit

DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map.

3D Hand Pose Estimation Data Augmentation

Learning to Align Semantic Segmentation and 2.5D Maps for Geolocalization

no code implementations CVPR 2017 Anil Armagan, Martin Hirzer, Peter M. Roth, Vincent Lepetit

We present an efficient method for geolocalization in urban environments starting from a coarse estimate of the location provided by a GPS and using a simple untextured 2. 5D model of the surrounding buildings.

Semantic Segmentation

Monocular LSD-SLAM Integration within AR System

2 code implementations8 Feb 2017 Markus Höll, Vincent Lepetit

In this paper, we cover the process of integrating Large-Scale Direct Simultaneous Localization and Mapping (LSD-SLAM) algorithm into our existing AR stereo engine, developed for our modified "Augmented Reality Oculus Rift".

Simultaneous Localization and Mapping

Training a Feedback Loop for Hand Pose Estimation

no code implementations ICCV 2015 Markus Oberweger, Paul Wohlhart, Vincent Lepetit

We propose an entirely data-driven approach to estimating the 3D pose of a hand given a depth image.

Hand Pose Estimation

Efficiently Creating 3D Training Data for Fine Hand Pose Estimation

1 code implementation CVPR 2016 Markus Oberweger, Gernot Riegler, Paul Wohlhart, Vincent Lepetit

While many recent hand pose estimation methods critically rely on a training set of labelled frames, the creation of such a dataset is a challenging task that has been overlooked so far.

Hand Pose Estimation

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.

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.

An Efficient Minimal Solution for Multi-Camera Motion

no code implementations ICCV 2015 Jonathan Ventura, Clemens Arth, Vincent Lepetit

We propose an efficient method for estimating the motion of a multi-camera rig from a minimal set of feature correspondences.

Motion Estimation

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

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.

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.

Global 6DOF Pose Estimation from Untextured 2D City Models

no code implementations9 Mar 2015 Clemens Arth, Christian Pirchheim, Jonathan Ventura, Vincent Lepetit

By contrast, our method returns an accurate, absolute camera pose in an absolute referential using simple 2D+height maps, which are broadly available, to refine a first estimate of the pose provided by the device's sensors.

Pose Estimation Semantic Segmentation +1

Hands Deep in Deep Learning for Hand Pose Estimation

1 code implementation24 Feb 2015 Markus Oberweger, Paul Wohlhart, Vincent Lepetit

We introduce and evaluate several architectures for Convolutional Neural Networks to predict the 3D joint locations of a hand given a depth map.

Deep Learning Hand Pose Estimation

Learning Descriptors for Object Recognition and 3D Pose Estimation

no code implementations CVPR 2015 Paul Wohlhart, Vincent Lepetit

Detecting poorly textured objects and estimating their 3D pose reliably is still a very challenging problem.

3D Pose Estimation Object +1

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.

Object

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.

Collision Avoidance General Classification +1

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.

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].

Clustering

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.

Robust 3D Tracking with Descriptor Fields

no code implementations CVPR 2014 Alberto Crivellaro, Vincent Lepetit

We introduce a method that can register challenging images from specular and poorly textured 3D environments, on which previous approaches fail.

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.

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.

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 Object Detection

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