Publications associées à Grouping explains contextual modulation in low level vision

Aggregating Spatial and Photometric Context for Photometric Stereo

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

3D reconstruction of curvilinear one-dimensional objects viewed in transmission electron microscopy

Gulnaz Ganeeva

To obtain a more complete understanding of material microstructure at the nanoscale and to gain profound insights into their properties, there is a growing need for more efficient and precise methods that can streamline the process of 3D imaging using a tr ...

EPFL2023

Detecting Anomalies and Obstacles in Road Scenes

Krzysztof Maciej Lis

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

EPFL2023

MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization

Alexandre Massoud Alahi, Sven Kreiss, Lorenzo Bertoni, Taylor Ferdinand Mordan

Monocular and stereo visions are cost-effective solutions for 3D human localization in the context of self-driving cars or social robots. However, they are usually developed independently and have their respective strengths and limitations. We propose a no ...

IEEE2021

Deep eyes: Joint depth inference using monocular and binocular cues

Siyuan Li, Chen Zhang, Yang Yang

Human visual system relies on both monocular focusness cues and binocular stereo cues to gain effective 3D perception. Correspondingly, depth from focus/defocus (DfF/DfD) and stereo matching are two most studied passive depth sensing schemes, which are tra ...

ELSEVIER2021

Crowding and the importance of grouping and segmentation processes in human vision

Alban Bornet

Human vision has evolved to make sense of a world in which elements almost never appear in isolation. Surprisingly, the recognition of an element in a visual scene is strongly limited by the presence of other nearby elements, a phenomenon known as visual c ...

EPFL2021

Beyond Cameras: Real-Time High-Resolution 3D and Panoramic MultiView Vision Systems with Their Applications

Bilal Demir

The cameras are invented by imitating the human visual system to capture the scene. The camera technologies have been substantially advanced in recent years. 108 MP resolution with 100x hybrid zoom has become standard features for smartphone flagships. In ...

EPFL2020

Learning stereo reconstruction with deep neural networks

Stepan Tulyakov

Stereo reconstruction is a problem of recovering a 3d structure of a scene from a pair of images of the scene, acquired from different viewpoints. It has been investigated for decades and many successful methods were developed. The main drawback of these ...

EPFL2020

Learning Symmetry with Tangible Robots

Francesco Mondada, Pierre Dillenbourg, Morgane Solène Denise Chevalier, Ayberk Özgür, Wafa Monia Benkaouar Johal

Robots bring a new potential for embodied learning in classrooms. With our project, we aim to ease the task for teachers and to show the worth of tangible manipulation of robots in educational contexts. In this article, we present the design and the evalua ...

SPRINGER INTERNATIONAL PUBLISHING AG2020

SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion

Jean-Philippe Thiran, Mohammad Saeed Rad, Seyedbehzad Bozorgtabar

Despite well-established baselines, learning of scene depth and ego-motion from monocular video remains an ongoing challenge, specifically when handling scaling ambiguity issues and depth inconsistencies in image sequences. Much prior work uses either a su ...

IEEE COMPUTER SOC2019

Solving the Depth Ambiguity in Single-Perspective Images

Sabine Süsstrunk, Marjan Shahpaski, Majed El Helou

Scene depth estimation is gaining in importance as more and more AR/VR and robot vision applications are developed. Conventional depth-from-defocus techniques can passively provide depth maps from a single image. This is especially advantageous for moving ...

2019

Are Existing Monocular Computer Vision-Based 3D Motion Capture Approaches Ready for Deployment? A Methodological Study on the Example of Alpine Skiing

Pascal Fua, Helge Jochen Rhodin, Mirela Ostrek

In this study, we compared a monocular computer vision (MCV)-based approach with the golden standard for collecting kinematic data on ski tracks (i.e., video-based stereophotogrammetry) and assessed its deployment readiness for answering applied research q ...

2019

A Real-Time Multi-Camera Depth Estimation ASIC with Custom On-Chip Embedded DRAM

Jonathan Emmanuel D Narinx

The capability to process high-resolution videos in real-time is becoming more important in a wide variety of applications such as autonomous vehicles, virtual reality or intelligent surveillance systems. The high-accuracy and complex video processing algo ...

EPFL2019

Towards Modelling of Visual Saliency in Point Clouds for Immersive Applications

Touradj Ebrahimi, Evangelos Alexiou, Peisen Xu

Modelling human visual attention is of great importance in the field of computer vision and has been widely explored for 3D imaging. Yet, in the absence of ground truth data, it is unclear whether such predictions are in alignment with the actual human vie ...

2019

Real-Time 3D Hand Pose Estimation with 3D Convolutional Neural Networks

Daniel Thalmann, Hui Liang

In this paper, we present a novel method for real-time 3D hand pose estimation from single depth images using 3D Convolutional Neural Networks (CNNs). Image-based features extracted by 2D CNNs are not directly suitable for 3D hand pose estimation due to th ...

IEEE COMPUTER SOC2019

Stereo-vision three-dimensional reconstruction of curvilinear structures imaged with a TEM

Pascal Fua, Marco Cantoni, Guillaume Lucas, Cécile Hébert, Emad Oveisi, Antoine Letouzey, Sandro Ivo Sebastiano De Zanet

Deriving accurate three-dimensional (3-D) structural information of materials at the nanometre level is often crucial for understanding their properties. Tomography in transmission electron microscopy (TEM) is a powerful technique that provides such inform ...

Elsevier2017

How grouping determines crowding

Michael Herzog

Crowding is traditionally thought to occur by local interactions between the target and the neighboring flankers, for example, by pooling neural responses corresponding to both the target and flankers. Accordingly, crowding is thought to occur within a sma ...

2017

Large-Scale Image Segmentation with Convolutional Networks

Pedro Henrique Oliveira Pinheiro

Object recognition is one of the most important problems in computer vision. However, visual recognition poses many challenges when tried to be reproduced by artificial systems. A main challenge is the problem of variability: objects can appear across huge ...

EPFL2017

Putting low-level vision into global context: Why vision cannot be reduced to basic circuits

Michael Herzog, Yvonne Evelina Thunell

To cope with the complexity of vision, most models in neuroscience and computer vision are of hierarchical and feedforward nature. Low-level vision, such as edge and motion detection, is explained by basic low-level neural circuits, whose outputs serve as ...

Elsevier2016

Child-Robot Spatial Arrangement in a Learning by Teaching Activity

Pierre Dillenbourg, Ana Paiva, Alexis David Jacq, Wafa Monia Benkaouar Johal

In this paper, we present an experiment in the context of a child-robot interaction where we study the influence of the child-robot spatial arrangement on the child’s focus of attention and the perception of the robot’s performance. In the “Co-Writer learn ...

Ieee2016