output
20022026
most citedLearning from Synthetic Humans

978 citations

Showing cs.CVShow all

39 papers · 1 filter

cs.CV2025

Optimal transport unlocks end-to-end learning for single-molecule localization

Romain Seailles, Jean-Baptiste Masson, Jean Ponce +1

Single-molecule localization microscopy (SMLM) allows reconstructing biology-relevant structures beyond the diffraction limit by detecting and localizing individual fluorophores --…

cs.CV2025

Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document

Adnan Ben Mansour, Ayoub Karine, David Naccache

Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Char…

cs.CV2024★ 1 cited

CNN Explainability with Multivector Tucker Saliency Maps for Self-Supervised Models

Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli +1

Interpreting the decisions of Convolutional Neural Networks (CNNs) is essential for understanding their behavior, yet explainability remains a significant challenge, particularly f…

cs.CV2024★ 1 cited

Detecting Looted Archaeological Sites from Satellite Image Time Series

Elliot Vincent, Mehraïl Saroufim, Jonathan Chemla +4

Archaeological sites are the physical remains of past human activity and one of the main sources of information about past societies and cultures. However, they are also the target…

cs.CV2024★ 1 cited

Satellite Image Time Series Semantic Change Detection: Novel Architecture and Analysis of Domain Shift

Elliot Vincent, Jean Ponce, Mathieu Aubry

Satellite imagery plays a crucial role in monitoring changes happening on Earth's surface and aiding in climate analysis, ecosystem assessment, and disaster response. In this paper…

cs.CV2023

Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation

Bruno Lecouat, Yann Dubois de Mont-Marin, Théo Bodrito +2

This paper introduces a novel approach to the fine alignment of images in a burst captured by a handheld camera. In contrast to traditional techniques that estimate two-dimensional…