b'Pascal Fua'

research

∙ 03/29/2022

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

Supervised approaches to 3D pose estimation from single images are remar...

Soumava Kumar Roy, et al. ∙

research

∙ 03/18/2022

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

Most recent 6D object pose estimation methods, including unsupervised on...

Yinlin Hu, et al. ∙

research

∙ 12/08/2021

Adversarial Parametric Pose Prior

The Skinned Multi-Person Linear (SMPL) model can represent a human body ...

Andrey Davydov, et al. ∙

research

∙ 12/06/2021

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

Deep learning-based approaches to delineating 3D structure depend on acc...

Doruk Öner, et al. ∙

research

∙ 12/02/2021

Overcoming the Domain Gap in Neural Action Representations

Relating animal behaviors to brain activity is a fundamental goal in neu...

Semih Günel, et al. ∙

research

∙ 12/01/2021

Dyadic Human Motion Prediction

Prior work on human motion forecasting has mostly focused on predicting ...

Isinsu Katircioglu, et al. ∙

research

∙ 11/29/2021

Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations

A fundamental goal in neuroscience is to understand the relationship bet...

Semih Günel, et al. ∙

research

∙ 11/29/2021

MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

Recent work modelling 3D open surfaces train deep neural networks to app...

Benoit Guillard, et al. ∙

research

∙ 11/17/2021

Learning to Align Sequential Actions in the Wild

State-of-the-art methods for self-supervised sequential action alignment...

Weizhe Liu, et al. ∙

research

∙ 11/12/2021

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

We propose a method for unsupervised reconstruction of a temporally-cons...

Jan Bednařík, et al. ∙

research

∙ 10/14/2021

3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks

Curvilinear structures frequently appear in microscopy imaging as the ob...

Okan Altingövde, et al. ∙

research

∙ 10/12/2021

Localized Persistent Homologies for more Effective Deep Learning

Persistent Homologies have been successfully used to increase the perfor...

Doruk Öner, et al. ∙

research

∙ 09/28/2021

DEBOSH: Deep Bayesian Shape Optimization

Shape optimization is at the heart of many industrial applications, such...

Nikita Durasov, et al. ∙

research

∙ 09/22/2021

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

CAD modeling typically involves the use of simple geometric primitives w...

Subeesh Vasu, et al. ∙

research

∙ 06/20/2021

DeepMesh: Differentiable Iso-Surface Extraction

Geometric Deep Learning has recently made striking progress with the adv...

Benoit Guillard, et al. ∙

research

∙ 06/07/2021

Weakly Supervised Volumetric Image Segmentation with Deformed Templates

There are many approaches that use weak-supervision to train networks to...

Udaranga Wickramasinghe, et al. ∙

research

∙ 04/30/2021

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

State-of-the-art semantic or instance segmentation deep neural networks ...

Robin Chan, et al. ∙

research

∙ 04/22/2021

Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning

We introduce a novel approach to unsupervised and semi-supervised domain...

Weizhe Liu, et al. ∙

research

∙ 04/14/2021

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

We propose a method for the unsupervised reconstruction of a temporally-...

Jan Bednařík, et al. ∙

research

∙ 04/08/2021

Robust Differentiable SVD

Eigendecomposition of symmetric matrices is at the heart of many compute...

Wei Wang, et al. ∙

research

∙ 04/01/2021

Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches

Reconstructing 3D shape from 2D sketches has long been an open problem b...

Benoit Guillard, et al. ∙

research

∙ 04/01/2021

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

6D pose estimation in space poses unique challenges that are not commonl...

Yinlin Hu, et al. ∙

research

∙ 03/30/2021

Leveraging Self-Supervision for Cross-Domain Crowd Counting

State-of-the-art methods for counting people in crowded scenes rely on d...

Weizhe Liu, et al. ∙

research

∙ 03/22/2021

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

The problem of estimating a surface shape from its observed reflectance ...

David Honzátko, et al. ∙

research

∙ 12/25/2020

Detecting Road Obstacles by Erasing Them

Vehicles can encounter a myriad of obstacles on the road, and it is not ...

Krzysztof Lis, et al. ∙

research

∙ 12/21/2020

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

Deep learning-solutions for hand-object 3D pose and shape estimation are...

Mengshi Qi, et al. ∙

research

∙ 12/15/2020

Masksembles for Uncertainty Estimation

Deep neural networks have amply demonstrated their prowess but estimatin...

Nikita Durasov, et al. ∙

research

∙ 12/09/2020

Self-supervised Human Detection and Segmentation via Multi-view Consensus

Self-supervised detection and segmentation of foreground objects in comp...

Isinsu Katircioglu, et al. ∙

research

∙ 12/08/2020

Long Term Motion Prediction Using Keyposes

Long term human motion prediction is an essential component in safety-cr...

Sena Kiciroglu, et al. ∙

research

∙ 12/02/2020

Unsupervised Learning on Monocular Videos for 3D Human Pose Estimation

In this paper, we introduce an unsupervised feature extraction method th...

Sina Honari, et al. ∙

research

∙ 12/01/2020

Counting People by Estimating People Flows

Modern methods for counting people in crowded scenes rely on deep networ...

Weizhe Liu, et al. ∙

research

∙ 11/27/2020

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

Local processing is an essential feature of CNNs and other neural networ...

Frank Yu, et al. ∙

research

∙ 11/23/2020

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

A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express ...

Shaifali Parashar, et al. ∙

research

∙ 11/17/2020

Deep Active Surface Models

Active Surface Models have a long history of being useful to model compl...

Udaranga Wickramasinghe, et al. ∙

research

∙ 11/11/2020

Self-supervised Segmentation via Background Inpainting

While supervised object detection and segmentation methods achieve impre...

Isinsu Katircioglu, et al. ∙

research

∙ 10/14/2020

Better Patch Stitching for Parametric Surface Reconstruction

Recently, parametric mappings have emerged as highly effective surface r...

Zhantao Deng, et al. ∙

research

∙ 10/06/2020

Motion Prediction Using Temporal Inception Module

Human motion prediction is a necessary component for many applications i...

Tim Lebailly, et al. ∙

research

∙ 09/15/2020

Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

We propose a novel, connectivity-oriented loss function for training dee...

Doruk Öner, et al. ∙

research

∙ 07/20/2020

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

In this paper, we tackle the problem of static 3D cloth draping on virtu...

Erhan Gundogdu, et al. ∙

research

∙ 07/17/2020

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

Most state-of-the-art approaches to road extraction from aerial images r...

Subeesh Vasu, et al. ∙

research

∙ 06/24/2020

DISK: Learning local features with policy gradient

Local feature frameworks are difficult to learn in an end-to-end fashion...

Michał J. Tyszkiewicz, et al. ∙

research

∙ 06/06/2020

MeshSDF: Differentiable Iso-Surface Extraction

Geometric Deep Learning has recently made striking progress with the adv...

Edoardo Remelli, et al. ∙

research

∙ 06/06/2020

UCLID-Net: Single View Reconstruction in Object Space

Most state-of-the-art deep geometric learning single-view reconstruction...

Benoit Guillard, et al. ∙

research

∙ 04/15/2020

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

Many classical Computer Vision problems, such as essential matrix comput...

Zheng Dang, et al. ∙

research

∙ 04/05/2020

Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation

We present a lightweight solution to recover 3D pose from multi-view ima...

Edoardo Remelli, et al. ∙

research

∙ 03/31/2020

Real-Time Camera Pose Estimation for Sports Fields

Given an image sequence featuring a portion of a sports field filmed by ...

Leonardo Citraro, et al. ∙

research

∙ 03/03/2020

Image Matching across Wide Baselines: From Paper to Practice

We introduce a comprehensive benchmark for local features and robust est...

Yuhe Jin, et al. ∙

research

∙ 01/23/2020

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

Our goal is to capture the pose of neuroscience model organisms, without...

Siyuan Li, et al. ∙

research

∙ 01/08/2020

Comparing Python, Go, and C++ on the N-Queens Problem

Python currently is the dominant language in the field of Machine Learni...

Pascal Fua, et al. ∙

research

∙ 12/18/2019

ActiveMoCap: Optimized Drone Flight for Active Human Motion Capture

The accuracy of monocular 3D human pose estimation depends on the viewpo...

Sena Kiciroglu, et al. ∙

Pascal Fua

Featured Co-authors