Published numerous papers covering topics such as image goal navigation, human mesh modeling, memory and pose in motion, multi-view stereo 3D reconstruction, hand-object 3D reconstruction, distilling a universal encoder, unconstrained 3D reconstruction, conditional multi-person mesh recovery, fully-integrated solution for unconstrained structure from motion, and multi-person whole-body human mesh recovery. Some of these papers have won awards, like the Best Student Paper Award for MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion.
Research Experience
Serves as a Principal Research Scientist at Naver Labs Europe, engaging in multiple research projects.
Background
Currently a Principal Research Scientist at Naver Labs Europe in the Computer Vision group. Research interests include (but are not limited to): representation learning (self-supervised learning, image retrieval, etc.), geometric vision (image matching, 3D reconstruction, etc.), and human-centric vision (human pose estimation, action recognition, etc.).