Loick Chambon

Affiliations Valeo.ai, Sorbonne University.

prof_pic.jpg

I am a Computer Vision PhD student at Sorbonne University and Valeo.ai, supervised by Matthieu Cord, Alexandre Boulch, and Eloi Zablocki.

My research focuses on feature upsampling and autonomous driving perception, with a particular interest in high-resolution visual representations, scalable 3D scene understanding, and efficient perception models for real-world applications.


💼 Open to job opportunities — feel free to reach out via email or social links below.

News

Nov 23, 2025 Preprint and code for NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering now available.
Sep 13, 2025 JAFAR: Jack up Any Feature at Any Resolution is accepted at NeurIPS 2025.
Sep 8, 2025 VaViM and VaVAM: Autonomous Driving through Video Generative Modeling has been accepted to CoRL 2025 Workshop LSRW.
Jul 7, 2025 GaussRender: Learning 3D Occupancy with Gaussian Rendering accepted paper at ICCV 2025.
Jun 17, 2024 PointBeV: A Sparse Approach to BeV Predictions accepted paper at CVPR 2024.
May 13, 2024 Towards motion forecasting with real-world perception inputs accepted paper at ICRA 2024.
Mar 8, 2023 PhD student at Sorbonne University and Valeo.ai.