Hi! I'm Nicolas, a recent PhD graduate from CVLab, EPFL, supervised by Prof. Pascal Fua. I have mostly worked on deep learning for 3D shape representation, with a focus on its application to shape design and optimization.
Before this, I did my Bachelor and Master degrees at EPFL, taking courses and projects related to robotics, computer vision, machine learning and deep learning.
You can check my up-to-date publication list on Google scholar.
Publications
Flow-Corrected Shape Optimization: Taming Manifold Drift in High-Dimensional 3D Models
Emilien Seiler, Nicolas Talabot, Yingxuan You, Federico Stella, Pascal Fua
NeurIPS 2026 [arXiv]
NeurIPS 2026 [arXiv]
S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
Deniz S. Mercadier*, Federico Stella*, Aurel Bizeau, Nicolas Talabot, Pascal Fua
NeurIPS 2026 [arXiv]
NeurIPS 2026 [arXiv]
Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulation
Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua
NeurIPS 2026 [arXiv]
NeurIPS 2026 [arXiv]
Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations
Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Ming Xu, Hieu Le, Pascal Fua
ECCV 2026 [arXiv]
ECCV 2026 [arXiv]
High Resolution UDF Meshing via Iterative Networks
Federico Stella, Nicolas Talabot, Hieu Le, Pascal Fua
NeurIPS 2025 [arXiv]
NeurIPS 2025 [arXiv]
Pairwise-Constrained Implicit Functions for 3D Human Heart Modeling
Hieu Le, Jingyi Xu, Nicolas Talabot, Jiancheng Yang, Pascal Fua
MICCAI 2025 [arXiv]
MICCAI 2025 [arXiv]
