papers

Publications (198)

cs.CV2019

Detecting the Unexpected via Image Resynthesis

Krzysztof Lis, Krishna Nakka, Pascal Fua +1

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we ta…

cs.CV2016

LIFT: Learned Invariant Feature Transform

Kwang Moo Yi, Eduard Trulls, Vincent Lepetit +1

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

cs.CV2026

Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates

Yingxuan You, Ren Li, Corentin Dumery +3

Reconstructing 3D clothed humans from monocular images and videos is a fundamental problem with applications in virtual try-on, avatar creation, and mixed reality. Despite signific…

cs.CV2019

Motion Capture from Pan-Tilt Cameras with Unknown Orientation

Roman Bachmann, Jörg Spörri, Pascal Fua +1

In sports, such as alpine skiing, coaches would like to know the speed and various biomechanical variables of their athletes and competitors. Existing methods use either body-worn…

cs.CV2020

Real-Time Camera Pose Estimation for Sports Fields

Leonardo Citraro, Pablo Márquez-Neila, Stefano Savarè +6

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 i…

cs.CV2019

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

Weizhe Liu, Krzysztof Lis, Mathieu Salzmann +1

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image-plane d…

cs.CV2023

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Zhen Wei, Pascal Fua, Michaël Bauerheim

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric lear…

cs.CV2021

Learning to Align Sequential Actions in the Wild

Weizhe Liu, Bugra Tekin, Huseyin Coskun +3

State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspondences across videos in time. They either learn frame-to-frame map…

cs.CV2016

Multi-Modal Mean-Fields via Cardinality-Based Clamping

Pierre Baqué, François Fleuret, Pascal Fua

Mean Field inference is central to statistical physics. It has attracted much interest in the Computer Vision community to efficiently solve problems expressible in terms of large…

stat.ML2025

Do you understand epistemic uncertainty? Think again! Rigorous frequentist epistemic uncertainty estimation in regression

Enrico Foglia, Benjamin Bobbia, Nikita Durasov +4

Quantifying model uncertainty is critical for understanding prediction reliability, yet distinguishing between aleatoric and epistemic uncertainty remains challenging. We extend re…

cs.LG2019

Backpropagation-Friendly Eigendecomposition

Wei Wang, Zheng Dang, Yinlin Hu +2

Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it…

cs.CV2018

Real-Time Seamless Single Shot 6D Object Pose Prediction

Bugra Tekin, Sudipta N. Sinha, Pascal Fua

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple…

cs.CV2022

HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation

Subeesh Vasu, Nicolas Talabot, Artem Lukoianov +3

Deep implicit surfaces excel at modeling generic shapes but do not always capture the regularities present in manufactured objects, which is something simple geometric primitives a…

cs.CV2018

LF-Net: Learning Local Features from Images

Yuki Ono, Eduard Trulls, Pascal Fua +1

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. To…

cs.LG2017

Learning Active Learning from Data

Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate samp…

cs.CV2021

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

Robin Chan, Krzysztof Lis, Svenja Uhlemeyer +6

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle pre…

cs.CV2020

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

Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller +7

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions…

cs.CV2021

Image Matching across Wide Baselines: From Paper to Practice

Yuhe Jin, Dmytro Mishkin, Anastasiia Mishchuk +4

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 o…

cs.CV2025

DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion

Hantao Zhang, Yuhe Liu, Jiancheng Yang +3

Accurate medical image segmentation is crucial for precise anatomical delineation. Deep learning models like U-Net have shown great success but depend heavily on large datasets and…

cs.CV2021

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

Jan Bednarik, Noam Aigerman, Vladimir G. Kim +4

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically…

cs.CV2018

FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification

Xiaoqing Yin, Xinchao Wang, Jun Yu +3

Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions. Rectification of fisheye images is therefore a crucial preprocessing step for m…

cs.CV2015

Template-based Monocular 3D Shape Recovery using Laplacian Meshes

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 o…

cs.CV2021

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

Frank Yu, Mathieu Salzmann, Pascal Fua +1

Local processing is an essential feature of CNNs and other neural network architectures - it is one of the reasons why they work so well on images where relevant information is, to…

cs.CV2021

Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations

Semih Günel, Florian Aymanns, Sina Honari +2

A fundamental goal in neuroscience is to understand the relationship between neural activity and behavior. For example, the ability to extract behavioral intentions from neural dat…

cs.CV2022

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

Yinlin Hu, Pascal Fua, Mathieu Salzmann

Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep…

cs.CV2023

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns

Ren Li, Benoît Guillard, Pascal Fua

Many approaches to draping individual garments on human body models are realistic, fast, and yield outputs that are differentiable with respect to the body shape on which they are…

cs.CV2018

What Face and Body Shapes Can Tell About Height

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 abse…

cs.CV2023

Detecting Road Obstacles by Erasing Them

Krzysztof Lis, Sina Honari, Pascal Fua +1

Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image patches and inpaint them…

cs.CV2022

Two-level Data Augmentation for Calibrated Multi-view Detection

Martin Engilberge, Haixin Shi, Zhiye Wang +1

Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view…

cs.CV2015

What Players do with the Ball: A Physically Constrained Interaction Modeling

Andrii Maksai, Xinchao Wang, Pascal Fua

Tracking the ball is critical for video-based analysis of team sports. However, it is difficult, especially in low-resolution images, due to the small size of the ball, its speed t…

cs.CV2021

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

David Honzátko, Engin Türetken, Pascal Fua +1

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

cs.RO2026

Gradient-based Nested Co-Design of Aerodynamic Shape and Control for Winged Robots

Daniele Affinita, Mingda Xu, Benoît Valentin Gherardi +1

Designing aerial robots for specialized tasks, from perching to payload delivery, requires tailoring their aerodynamic shape to specific mission requirements. For tasks involving w…

cs.CV2022

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

Sina Honari, Victor Constantin, Helge Rhodin +2

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame…

cs.CV2015

Active Learning for Delineation of Curvilinear Structures

Agata Mosinska, Raphael Sznitman, Przemysław Głowacki +1

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

cs.CV2024

AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains

Krzysztof Lis, Matthias Rottmann, Annika Mütze +3

In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this informat…

cs.CV2017

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

Bugra Tekin, Pablo Márquez-Neila, Mathieu Salzmann +1

Most recent approaches to monocular 3D human pose estimation rely on Deep Learning. They typically involve regressing from an image to either 3D joint coordinates directly or 2D jo…

cs.CV2026

Limited-Angle Tomography Reconstruction via Projector Guided 3D Diffusion

Zhantao Deng, Mériem Er-Rafik, Anna Sushko +2

Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted range and number of tilting angles…

cs.CV2025

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

Aoxiang Fan, Corentin Dumery, Nicolas Talabot +1

Neural Radiance Fields (NeRF) has emerged as a compelling framework for scene representation and 3D recovery. To improve its performance on real-world data, depth regularizations h…

cs.CV2015

TILDE: A Temporally Invariant Learned DEtector

Yannick Verdie, Kwang Moo Yi, Pascal Fua +1

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…

cs.CV2021

Adversarial Parametric Pose Prior

Andrey Davydov, Anastasia Remizova, Victor Constantin +3

The Skinned Multi-Person Linear (SMPL) model can represent a human body by mapping pose and shape parameters to body meshes. This has been shown to facilitate inferring 3D human po…

cs.CV2017

Imposing Hard Constraints on Deep Networks: Promises and Limitations

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. Such constr…

cs.CV2025

Gradient Distance Function

Hieu Le, Federico Stella, Benoit Guillard +1

Unsigned Distance Functions (UDFs) can be used to represent non-watertight surfaces in a deep learning framework. However, UDFs tend to be brittle and difficult to learn, in part b…

cs.CV2020

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

Doruk Oner, Mateusz Koziński, Leonardo Citraro +3

We propose a novel, connectivity-oriented loss function for training deep convolutional networks to reconstruct network-like structures, like roads and irrigation canals, from aeri…

cs.CV2026

VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSets

Yihong Chen, Pascal Fua

Accurate cardiac anatomy modeling requires the model to be able to handle intricate interrelations among structures. In this paper, we propose VecHeart, a unified framework for hol…

cs.CV2021

Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

Benoit Guillard, Edoardo Remelli, Pierre Yvernay +1

Reconstructing 3D shape from 2D sketches has long been an open problem because the sketches only provide very sparse and ambiguous information. In this paper, we use an encoder/dec…

cs.GR2025

High Resolution UDF Meshing via Iterative Networks

Federico Stella, Nicolas Talabot, Hieu Le +1

Unsigned Distance Fields (UDFs) are a natural implicit representation for open surfaces but, unlike Signed Distance Fields (SDFs), are challenging to triangulate into explicit mesh…

cs.CV2024

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

Andrey Davydov, Alexey Sidnev, Artsiom Sanakoyeu +3

When enough annotated training data is available, supervised deep-learning algorithms excel at estimating human body pose and shape using a single camera. The effects of too little…

cs.AI2026

WindINR: Latent-State INR for Fast Local Wind Query and Correction in Complex Terrain

Yi Xiao, Qilong Jia, Hang Fan +4

Many downstream decisions in complex terrain require fast wind estimates at a small number of user-specified locations and heights for a given forecast valid time, rather than anot…

cs.CV2023

State of the Art in Dense Monocular Non-Rigid 3D Reconstruction

Edith Tretschk, Navami Kairanda, Mallikarjun B R +7

3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics.…

cs.CV2020

Estimating People Flows to Better Count Them in Crowded Scenes

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. As such, only very few take advantage of temporal cons…

cs.CV2019

Beyond Cartesian Representations for Local Descriptors

Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi +2

The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if…

cs.CV2014

On Rendering Synthetic Images for Training an Object Detector

Artem Rozantsev, Vincent Lepetit, Pascal Fua

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering…

cs.CV2024

Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft

Jakub Gwizdała, Doruk Oner, Soumava Kumar Roy +6

Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft's surroundings and to provide t…

cs.CV2022

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

Doruk Oner, Leonardo Citraro, Mateusz Koziński +1

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet, in practice, people, no matter how conscientious, have trouble…

cs.CV2020

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

Siyuan Li, Semih Günel, Mirela Ostrek +3

Our goal is to capture the pose of neuroscience model organisms, without using any manual supervision, to be able to study how neural circuits orchestrate behaviour. Human pose est…

cs.CV2024

Unsupervised 3D Keypoint Discovery with Multi-View Geometry

Sina Honari, Chen Zhao, Mathieu Salzmann +1

Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or vi…

cs.CV2016

Do We Need Binary Features for 3D Reconstruction?

Bin Fan, Qingqun Kong, Wei Sui +5

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 descriptor…

cs.CV2024

Reconstruction of Manipulated Garment with Guided Deformation Prior

Ren Li, Corentin Dumery, Zhantao Deng +1

Modeling the shape of garments has received much attention, but most existing approaches assume the garments to be worn by someone, which constrains the range of shapes they can as…

cs.CV2015

Predicting People's 3D Poses from Short Sequences

Bugra Tekin, Xiaolu Sun, Xinchao Wang +2

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

cs.CV2022

Overcoming the Domain Gap in Neural Action Representations

Semih Günel, Florian Aymanns, Sina Honari +2

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

cs.CV2026

The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Counting

Corentin Dumery, Niki Amini-Naieni, Shervin Naini +1

Object counting is a foundational vision task with over a decade of dedicated research, yet state-of-the-art models still fail systematically in the mixed-object setting that domin…

cs.CV2021

Wide-Depth-Range 6D Object Pose Estimation in Space

Yinlin Hu, Sebastien Speierer, Wenzel Jakob +2

6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting. One of the most striking differences is the lack of atmospheric sc…

cs.CV2017

Beyond the Pixel-Wise Loss for Topology-Aware Delineation

Agata Mosinska, Pablo Marquez-Neila, Mateusz Kozinski +1

Delineation of curvilinear structures is an important problem in Computer Vision with multiple practical applications. With the advent of Deep Learning, many current approaches on…

cs.AI2013

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

Pascal Fua

To develop an approach to utilizing continuous statistical information within the Dempster- Shafer framework, we combine methods proposed by Strat and by Shafero We first derive co…

cs.CV2022

3D Pose Based Feedback for Physical Exercises

Ziyi Zhao, Sena Kiciroglu, Hugues Vinzant +4

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mi…

cs.CV2021

Robust Differentiable SVD

Wei Wang, Zheng Dang, Yinlin Hu +2

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms. However, the derivatives of the eigenvectors tend to be numerically unstable, whether u…

cs.CV2022

Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis

Jiancheng Yang, Rui Shi, Udaranga Wickramasinghe +3

The human annotations are imperfect, especially when produced by junior practitioners. Multi-expert consensus is usually regarded as golden standard, while this annotation protocol…

cs.CV2024

Garment Recovery with Shape and Deformation Priors

Ren Li, Corentin Dumery, Benoît Guillard +1

While modeling people wearing tight-fitting clothing has made great strides in recent years, loose-fitting clothing remains a challenge. We propose a method that delivers realistic…

cs.CV2020

Single-Stage 6D Object Pose Estimation

Yinlin Hu, Pascal Fua, Wei Wang +1

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a R…

cs.CV2025

Counting Stacked Objects

Corentin Dumery, Noa Etté, Aoxiang Fan +4

Visual object counting is a fundamental computer vision task underpinning numerous real-world applications, from cell counting in biomedicine to traffic and wildlife monitoring. Ho…

cs.CV2018

Every Smile is Unique: Landmark-Guided Diverse Smile Generation

Wei Wang, Xavier Alameda-Pineda, Dan Xu +3

Each smile is unique: one person surely smiles in different ways (e.g., closing/opening the eyes or mouth). Given one input image of a neutral face, can we generate multiple smile…

cs.CV2025

High-Fidelity and Generalizable Neural Surface Reconstruction with Sparse Feature Volumes

Aoxiang Fan, Corentin Dumery, Nicolas Talabot +2

Generalizable neural surface reconstruction has become a compelling technique to reconstruct from few images without per-scene optimization, where dense 3D feature volume has prove…

cs.CV2024

No Identity, no problem: Motion through detection for people tracking

Martin Engilberge, F. Wilke Grosche, Pascal Fua

Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models an…

eess.IV2024

LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models

Hantao Zhang, Yuhe Liu, Jiancheng Yang +4

Patient data from real-world clinical practice often suffers from data scarcity and long-tail imbalances, leading to biased outcomes or algorithmic unfairness. This study addresses…

cs.CV2022

Long Term Motion Prediction Using Keyposes

Sena Kiciroglu, Wei Wang, Mathieu Salzmann +1

Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving. In this paper we show that to achieve long te…

cs.CV2019

Probabilistic Atlases to Enforce Topological Constraints

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). However, their use…

cs.LG2026

Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling

Hantao Zhang, Jieke Wu, Mingda Xu +3

For multivariate co-generation in scientific applications, we advocate pairwise block rather than joint modeling of all variables. This design mitigates the computational burden an…

cs.CV2024

A Latent Implicit 3D Shape Model for Multiple Levels of Detail

Benoit Guillard, Marc Habermann, Christian Theobalt +1

Implicit neural representations map a shape-specific latent code and a 3D coordinate to its corresponding signed distance (SDF) value. However, this approach only offers a single l…

cs.CV2022

Multi-view Tracking Using Weakly Supervised Human Motion Prediction

Martin Engilberge, Weizhe Liu, Pascal Fua

Multi-view approaches to people-tracking have the potential to better handle occlusions than single-view ones in crowded scenes. They often rely on the tracking-by-detection paradi…

cs.CV2022

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

Benoit Guillard, Federico Stella, Pascal Fua

Unsigned Distance Fields (UDFs) can be used to represent non-watertight surfaces. However, current approaches to converting them into explicit meshes tend to either be expensive or…

cs.CV2024

CLOAF: CoLlisiOn-Aware Human Flow

Andrey Davydov, Martin Engilberge, Mathieu Salzmann +1

Even the best current algorithms for estimating body 3D shape and pose yield results that include body self-intersections. In this paper, we present CLOAF, which exploits the diffe…

cs.CV2019

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

Didier Bieler, Semih Günel, Pascal Fua +1

Estimating the metric height of a person from monocular imagery without additional assumptions is ill-posed. Existing solutions either require manual calibration of ground plane an…

cs.CV2026

GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks

Hantao Zhang, Weidong Guo, Yuhe Liu +5

Data-driven medical AI is traditionally formulated as a discriminative mapping from input to output via a learned function , which does not generalize well across hetero…

cs.CV2020

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

Erhan Gundogdu, Victor Constantin, Shaifali Parashar +4

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of…

cs.CV2026

Automated Counting of Stacked Objects in Industrial Inspection

Corentin Dumery, Noa Etté, Aoxiang Fan +4

Visual object counting is a fundamental computer vision task in industrial inspection, where accurate, high-throughput inventory tracking and quality assurance are critical. Moreov…

cs.CV2022

Enforcing connectivity of 3D linear structures using their 2D projections

Doruk Oner, Hussein Osman, Mateusz Kozinski +1

Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural ne…

cs.CV2017

Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection

Pierre Baqué, François Fleuret, Pascal Fua

People detection in single 2D images has improved greatly in recent years. However, comparatively little of this progress has percolated into multi-camera multi-people tracking alg…

cs.CV2023

MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision

Jianning Li, Zongwei Zhou, Jiancheng Yang +154

Prior to the deep learning era, shape was commonly used to describe the objects. Nowadays, state-of-the-art (SOTA) algorithms in medical imaging are predominantly diverging from co…

cs.CV2017

The WILDTRACK Multi-Camera Person Dataset

Tatjana Chavdarova, Pierre Baqué, Stéphane Bouquet +6

People detection methods are highly sensitive to the perpetual occlusions among the targets. As multi-camera set-ups become more frequently encountered, joint exploitation of the a…

cs.CV2018

Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation

Wei Wang, Kaicheng Yu, Joachim Hugonot +2

As mixed reality is gaining increased momentum, the development of effective and efficient solutions to egocentric hand segmentation is becoming critical. Traditional segmentation…

cs.CV2024

Neural Surface Detection for Unsigned Distance Fields

Federico Stella, Nicolas Talabot, Hieu Le +1

Extracting surfaces from Signed Distance Fields (SDFs) can be accomplished using traditional algorithms, such as Marching Cubes. However, since they rely on sign flips across the s…

cs.CE2025

Dflow-SUR: Enhancing Generative Aerodynamic Inverse Design using Differentiation Throughout Flow Matching

Aobo Yang, Zhen Wei, Rhea Liem +1

Generative inverse design requires incorporating physical constraints to ensure that generated designs are both reliable and accurate. However, we observe that current state-of-the…

cs.CV2025

PrIntMesh: Precise Intersection Surfaces for 3D Organ Mesh Reconstruction

Deniz Sayin Mercadier, Hieu Le, Yihong Chen +3

Human organs are composed of interconnected substructures whose geometry and spatial relationships constrain one another. Yet, most deep-learning approaches treat these parts indep…

cs.RO2022

Learning to Simulate Realistic LiDARs

Benoit Guillard, Sai Vemprala, Jayesh K. Gupta +4

Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics mod…

cs.CV2022

Dyadic Human Motion Prediction

Isinsu Katircioglu, Costa Georgantas, Mathieu Salzmann +1

Prior work on human motion forecasting has mostly focused on predicting the future motion of single subjects in isolation from their past pose sequence. In the presence of closely…

cs.LG2019

Discovering General-Purpose Active Learning Strategies

Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

We propose a general-purpose approach to discovering active learning (AL) strategies from data. These strategies are transferable from one domain to another and can be used in conj…

cs.CE2018

Geodesic Convolutional Shape Optimization

Pierre Baqué, Edoardo Remelli, François Fleuret +1

Aerodynamic shape optimization has many industrial applications. Existing methods, however, are so computationally demanding that typical engineering practices are to either simply…

cs.CV2017

Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery

Thomas Kurmann, Pablo Marquez Neila, Xiaofei Du +4

Detection of surgical instruments plays a key role in ensuring patient safety in minimally invasive surgery. In this paper, we present a novel method for 2D vision-based recognitio…

cs.CV2019

Neural Scene Decomposition for Multi-Person Motion Capture

Helge Rhodin, Victor Constantin, Isinsu Katircioglu +2

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networ…

cs.CV2019

Recurrent U-Net for Resource-Constrained Segmentation

Wei Wang, Kaicheng Yu, Joachim Hugonot +2

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 sta…