Corentin Dumery

Corentin Dumery is a Doctoral Assistant at École Polytechnique Fédérale de Lausanne (EPFL), affiliated with the Computer Vision Laboratory (CVLAB) and Machine Learning and Optimization Laboratory (MLO) within the School of Computer and Communication Sciences. His research bridges Computer Vision and Computer Graphics, focusing on 3D scene reconstruction, garment modeling, and neural rendering techniques. Previously, he interned at Meta Redmond, worked at CEA Paris-Saclay on polycube mapping, and was a visiting researcher at ETH Zurich under Prof. Olga Sorkine-Hornung.

Corentin holds dual MSc degrees in Computer Science from National University of Singapore (NUS) and Télécom Paris. His work emphasizes

• 3D content creation for AR/VR
• Diffusion models for garment reconstruction
• Neural radiance field optimization
• Polycube mapping for hexahedral meshing

His recent publications (2022–2025) span top venues like SIGGRAPH, ICCV, and CVPR, addressing challenges in 3D Gaussian splatting, view-consistent NeRF training, and single-view garment recovery. He also contributes to academic service as an Outstanding Reviewer at CVPR25 and co-organizes workshops like OpenSUN3D.

At EPFL, he serves as Head Teaching Assistant for courses CS433 Machine Learning (2023–2024) and CS442 Computer Vision (2023–2024). Additionally, he is the VP/Treasurer of EPIC, EPFL's computer science PhD association.