Pascal Fua

is this you? claim profile

∙ 0 followers
EPFL

Professor at EPFL (École polytechnique fédérale de Lausanne)

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

Local processing is an essential feature of CNNs and other neural networ...
11/27/2020 ∙ by Frank Yu, et al. ∙ 0 ∙ share

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

A recent trend in Non-Rigid Structure-from-Motion (NRSfM) is to express ...
11/23/2020 ∙ by Shaifali Parashar, et al. ∙ 0 ∙ share

read it
Deep Active Surface Models

Active Surface Models have a long history of being useful to model compl...
11/17/2020 ∙ by Udaranga Wickramasinghe, et al. ∙ 0 ∙ share

read it
Self-supervised Segmentation via Background Inpainting

While supervised object detection and segmentation methods achieve impre...
11/11/2020 ∙ by Isinsu Katircioglu, et al. ∙ 0 ∙ share

read it
Better Patch Stitching for Parametric Surface Reconstruction

Recently, parametric mappings have emerged as highly effective surface r...
10/14/2020 ∙ by Zhantao Deng, et al. ∙ 0 ∙ share

read it
Motion Prediction Using Temporal Inception Module

Human motion prediction is a necessary component for many applications i...
10/06/2020 ∙ by Tim Lebailly, et al. ∙ 1 ∙ share

read it
Promoting Connectivity of Network-Like Structures by Enforcing Region Separation

We propose a novel, connectivity-oriented loss function for training dee...
09/15/2020 ∙ by Doruk Öner, et al. ∙ 0 ∙ share

read it
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...
07/20/2020 ∙ by Erhan Gundogdu, et al. ∙ 0 ∙ share

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

Most state-of-the-art approaches to road extraction from aerial images r...
07/17/2020 ∙ by Subeesh Vasu, et al. ∙ 0 ∙ share

read it
DISK: Learning local features with policy gradient

Local feature frameworks are difficult to learn in an end-to-end fashion...
06/24/2020 ∙ by Michał J. Tyszkiewicz, et al. ∙ 0 ∙ share

read it
MeshSDF: Differentiable Iso-Surface Extraction

Geometric Deep Learning has recently made striking progress with the adv...
06/06/2020 ∙ by Edoardo Remelli, et al. ∙ 7 ∙ share

read it
UCLID-Net: Single View Reconstruction in Object Space

Most state-of-the-art deep geometric learning single-view reconstruction...
06/06/2020 ∙ by Benoit Guillard, et al. ∙ 0 ∙ share

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

Many classical Computer Vision problems, such as essential matrix comput...
04/15/2020 ∙ by Zheng Dang, et al. ∙ 0 ∙ share

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

We present a lightweight solution to recover 3D pose from multi-view ima...
04/05/2020 ∙ by Edoardo Remelli, et al. ∙ 0 ∙ share

read it
Real-Time Camera Pose Estimation for Sports Fields

Given an image sequence featuring a portion of a sports field filmed by ...
03/31/2020 ∙ by Leonardo Citraro, et al. ∙ 0 ∙ share

read it
Image Matching across Wide Baselines: From Paper to Practice

We introduce a comprehensive benchmark for local features and robust est...
03/03/2020 ∙ by Yuhe Jin, et al. ∙ 36 ∙ share

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

Our goal is to capture the pose of neuroscience model organisms, without...
01/23/2020 ∙ by Siyuan Li, et al. ∙ 4 ∙ share

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

Python currently is the dominant language in the field of Machine Learni...
01/08/2020 ∙ by Pascal Fua, et al. ∙ 0 ∙ share

read it
ActiveMoCap: Optimized Drone Flight for Active Human Motion Capture

The accuracy of monocular 3D human pose estimation depends on the viewpo...
12/18/2019 ∙ by Sena Kiciroglu, et al. ∙ 0 ∙ share

read it
VM-Net: Mesh Modeling to Assist Segmentation in Volumetric Data

CNN-based volumetric methods that label individual voxels now dominate t...
12/08/2019 ∙ by Udaranga Wickramasinghe, et al. ∙ 0 ∙ share

read it
Towards Reliable Evaluation of Road Network Reconstructions

Existing performance measures rank delineation algorithms inconsistently...
11/28/2019 ∙ by Leonardo Citraro, et al. ∙ 0 ∙ share

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

State-of-the-art methods for counting people in crowded scenes rely on d...
11/26/2019 ∙ by Weizhe Liu, et al. ∙ 10 ∙ share

read it
Shape Reconstruction by Learning Differentiable Surface Representations

Generative models that produce point clouds have emerged as a powerful t...
11/25/2019 ∙ by Jan Bednařík, et al. ∙ 24 ∙ share

read it
Estimating People Flows to Better Count them in Crowded Scenes

State-of-the-art methods for counting people in crowded scenes rely on d...
11/25/2019 ∙ by Weizhe Liu, et al. ∙ 36 ∙ share

read it
Single-Stage 6D Object Pose Estimation

Most recent 6D pose estimation frameworks first rely on a deep network t...
11/19/2019 ∙ by Yinlin Hu, et al. ∙ 0 ∙ share

read it
Probabilistic Atlases to Enforce Topological Constraints

Probabilistic atlases (PAs) have long been used in standard segmentation...
09/18/2019 ∙ by Udaranga Wickramasinghe, et al. ∙ 0 ∙ share

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

Estimating the metric height of a person from monocular imagery without ...
09/05/2019 ∙ by Didier Bieler, et al. ∙ 0 ∙ share

read it
Motion Capture from Pan-Tilt Cameras with Unknown Orientation

In sports, such as alpine skiing, coaches would like to know the speed a...
08/30/2019 ∙ by Roman Bachmann, et al. ∙ 4 ∙ share

read it
Beyond Cartesian Representations for Local Descriptors

The dominant approach for learning local patch descriptors relies on sma...
08/15/2019 ∙ by Patrick Ebel, et al. ∙ 2 ∙ share

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

While supervised object detection methods achieve impressive accuracy, t...
07/18/2019 ∙ by Isinsu Katircioglu, et al. ∙ 6 ∙ share

read it
XNect: Real-time Multi-person 3D Human Pose Estimation with a Single RGB Camera

We present a real-time approach for multi-person 3D motion capture at ov...
07/01/2019 ∙ by Dushyant Mehta, et al. ∙ 13 ∙ share

read it
Backpropagation-Friendly Eigendecomposition

Eigendecomposition (ED) is widely used in deep networks. However, the ba...
06/21/2019 ∙ by Wei Wang, et al. ∙ 0 ∙ share

read it
Recurrent U-Net for Resource-Constrained Segmentation

State-of-the-art segmentation methods rely on very deep networks that ar...
06/11/2019 ∙ by Wei Wang, et al. ∙ 0 ∙ share

read it
Joint Segmentation and Path Classification of Curvilinear Structures

Detection of curvilinear structures in images has long been of interest....
05/09/2019 ∙ by Agata Mosinska, et al. ∙ 0 ∙ share

read it
Detecting the Unexpected via Image Resynthesis

Classical semantic segmentation methods, including the recent deep learn...
04/16/2019 ∙ by Krzysztof Lis, et al. ∙ 36 ∙ share

read it
Neural Scene Decomposition for Multi-Person Motion Capture

Learning general image representations has proven key to the success of ...
03/13/2019 ∙ by Helge Rhodin, et al. ∙ 10 ∙ share

read it
NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler

Most algorithms that rely on deep learning-based approaches to generate ...
01/27/2019 ∙ by Edoardo Remelli, et al. ∙ 0 ∙ share

read it
Segmentation-driven 6D Object Pose Estimation

The most recent trend in estimating the 6D pose of rigid objects has bee...
12/06/2018 ∙ by Yinlin Hu, et al. ∙ 12 ∙ share

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

Identity Switching remains one of the main difficulties Multiple Object ...
11/27/2018 ∙ by Andrii Maksai, et al. ∙ 0 ∙ share

read it
GarNet: A Two-stream Network for Fast and Accurate 3D Cloth Draping

While Physics-Based Simulation (PBS) can highly accurately drape a 3D ga...
11/27/2018 ∙ by Erhan Gundogdu, et al. ∙ 0 ∙ share

read it
Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation

As mixed reality is gaining increased momentum, the development of effec...
11/27/2018 ∙ by Wei Wang, et al. ∙ 0 ∙ share

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

The difficulty of obtaining annotations to build training databases stil...
11/26/2018 ∙ by Mateusz Kozinski, et al. ∙ 0 ∙ share

read it
Context-Aware Crowd Counting

State-of-the-art methods for counting people in crowded scenes rely on d...
11/26/2018 ∙ by Weizhe Liu, et al. ∙ 2 ∙ share

read it
Discovering General-Purpose Active Learning Strategies

We propose a general-purpose approach to discovering active learning (AL...
10/09/2018 ∙ by Ksenia Konyushkova, et al. ∙ 0 ∙ share

read it
What Face and Body Shapes Can Tell About Height

Recovering a person's height from a single image is important for virtua...
05/25/2018 ∙ by Semih Günel, et al. ∙ 0 ∙ share

read it
LF-Net: Learning Local Features from Images

We present a novel deep architecture and a training strategy to learn a ...
05/24/2018 ∙ by Yuki Ono, et al. ∙ 0 ∙ share

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

Images captured by fisheye lenses violate the pinhole camera assumption ...
04/13/2018 ∙ by Xiaoqing Yin, et al. ∙ 0 ∙ share

read it
Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

Modern 3D human pose estimation techniques rely on deep networks, which ...
04/03/2018 ∙ by Helge Rhodin, et al. ∙ 0 ∙ share

read it
Learning Shape-from-Shading for Deformable Surfaces

Recent years have seen the development of mature solutions for reconstru...
03/23/2018 ∙ by Jan Bednařík, et al. ∙ 0 ∙ share

read it
Geometric and Physical Constraints for Head Plane Crowd Density Estimation in Videos

State-of-the-art methods of people counting in crowded scenes rely on de...
03/23/2018 ∙ by Weizhe Liu, et al. ∙ 0 ∙ share

read it

Pascal Fua

Featured Co-authors