Publication
A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth and Optical Flow Estimation
Related publications (47)
Burst Vision Using Single-Photon Cameras
Edoardo Charbon, Paul Mos, Mohit Gupta
Single-photon avalanche diodes (SPADs) are novel image sensors that record the arrival of individual photons at extremely high temporal resolution. In the past, they were only available as single pixels or small-format arrays, for various active imaging ap ...
IEEE COMPUTER SOC2023Automated Human Motion Analysis and Synthesis
Human motion analysis and synthesis is integral to many computer vision applications, from autonomous driving to sports analysis. In this thesis, we address several problems in this domain. First we consider active viewpoint selection for pose estimation w ...
EPFL2023Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
Kathrin Grosse, Sebastiano Vascon
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative of the data that ...
2023Processing load, and not stimulus evidence, determines the duration of unconscious visual feature integration
Michael Herzog, Leila Drissi Daoudi - Kleinbauer, Lukas Vogelsang
Integration across space and time is essential for the analysis of motion, low contrast, and many more stimuli. A crucial question is what determines the duration of integration. Based on classical models of decision-making, one might expect that integrati ...
2023Lidar point-to-point correspondences for rigorous registration of kinematic scanning in dynamic networks
Jan Skaloud, Davide Antonio Cucci, Aurélien Arnaud Brun
With the objective of improving the registration of lidar point clouds produced by kinematic scanning systems, we propose a novel trajectory adjustment procedure that leverages on the automated extraction of selected reliable 3D point–to–point corresponden ...
2022Structure-aware Multi-view 3D Reconstruction of Dislocations in TEM with Message Passing Neural Networks
Pascal Fua, Cécile Hébert, Emad Oveisi, Gulnaz Ganeeva, Anastasiia Mishchuk, Okan Altingövde
Efficient analysis of the three-dimensional (3D) shape and distribution of curvilinear crystal defects, namely dislocations, is an open research topic in material science and computer vision. In order to determine the structural and opto-electrical charact ...
2021DepthInSpace: Exploitation and Fusion of Multiple Video Frames for Structured-Light Depth Estimation
François Fleuret, Camilla Carta
We present DepthInSpace, a self-supervised deep-learning method for depth estimation using a structured-light camera. The design of this method is motivated by the commercial use case of embedded depth sensors in nowadays smartphones. We first propose to u ...
IEEE2021Perspectives on Individual Animal Identification from Biology and Computer Vision
Alexander Mathis, Maxime Michel André Vidal
Identifying individual animals is crucial for many biological investigations. In response to some of the limitations of current identification methods, new automated computer vision approaches have emerged with strong performance. Here, we review current a ...
OXFORD UNIV PRESS INC2021VIODE: A Simulated Dataset to Address the Challenges of Visual-Inertial Odometry in Dynamic Environments
Dario Floreano, Valentin Wüest, Fabian Maximilian Schilling, Koji Minoda
Dynamic environments such as urban areas are still challenging for popular visual-inertial odometry (VIO) algorithms. Existing datasets typically fail to capture the dynamic nature of these environments, therefore making it difficult to quantitatively eval ...
2021Beyond Cameras: Real-Time High-Resolution 3D and Panoramic MultiView Vision Systems with Their Applications
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