Antoine Guédon

PhD Student

IMAGINE / LIGM
École des Ponts ParisTech (ENPC)

6-8, Av Blaise Pascal - Cité Descartes
Champs-sur-Marne
77455 Marne-la-Vallée cedex 2
France
✉ antoine (dot) guedon (at) enpc.fr

Profile picture

Introduction


I am a PhD student in the IMAGINE computer vision team of École des Ponts ParisTech (ENPC) and I am co-advised by Vincent Lepetit (ENPC) and Pascal Monasse (ENPC). I am mostly interested in Image-Based Rendering (IBR) and 3D reconstruction using deep learning approaches. In particular, I worked on developing scalable approaches for simultaneously learning to reconstruct and explore 3D environments. More recently, I have been working on Novel View Synthesis and surface reconstruction in radiance fields. Before that, I studied at the Ecole polytechnique as well as the École normale supérieure Paris-Saclay where I obtained the MVA MS degree.

News


03-2024

I was invited by George Kopanas and Bernard Kerbl to give a talk about Surface Reconstruction using Gaussian Splatting during the 3DV 2024 tutorial on Gaussian Splatting.

02-2024

SuGaR paper has been accepted to CVPR 2024!

03-2023

MACARONS paper has been accepted to CVPR 2023!

11-2022

SCONE paper has received a Spotlight at NeurIPS 2022!

08-2022

SCONE paper has been accepted to NeurIPS 2022!

09-2021

I'm starting my PhD!

Publications


Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

arXiv 2024

Antoine Guédon, Vincent Lepetit
We propose to represent surfaces by a mesh covered with a "Frosting" layer of varying thickness and made of 3D Gaussians. This representation captures both complex volumetric effects created by fuzzy materials such as hair or grass as well as flat surfaces. Built from RGB images only, it can be rendered in real-time and animated using traditional animation tools.
  Paper   Code (coming soon)
                                @article{guedon2024frosting,
                                    title={Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering},
                                    author={Gu{\'e}don, Antoine and Lepetit, Vincent},
                                    journal={arXiv preprint arXiv:2403.14554},
                                    year={2024}
                              }
                        

SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

CVPR 2024

Antoine Guédon, Vincent Lepetit
We introduce a method that extracts accurate and editable meshes from 3D Gaussian Splatting representations within minutes on a single GPU. This enables easy editing, sculpting, rigging, animating, or relighting of the Gaussians using traditional softwares (Blender, Unity, Unreal Engine, etc.) by manipulating the mesh instead of the Gaussians themselves.
  Paper   Code
                                @misc{guedon2023sugar,
                                    title={SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering}, 
                                    author={Antoine Gu├ędon and Vincent Lepetit},
                                    year={2023},
                                    eprint={2311.12775},
                                    archivePrefix={arXiv},
                                    primaryClass={cs.GR}
                              }
                        

MACARONS: Mapping And Coverage Anticipation with RGB ONline Self-supervision

CVPR 2023

Antoine Guédon, Tom Monnier, Pascal Monasse, Vincent Lepetit
We introduce a novel method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only, in a self-supervised fashion.
  Paper   Code
                                @inproceedings{guedon2023macarons,
                                    title={{MACARONS: Mapping And Coverage Anticipation with RGB ONline Self-supervision}},
                                    author={Guédon, Antoine and Monnier, Tom and Monasse, Pascal and Lepetit, Vincent},
                                    booktitle={{CVPR}},
                                    year={2023},
                                }
                            

SCONE: Surface Coverage Optimization in uNknown Environments by Volumetric Integration

NeurIPS 2022 (Spotlight)

Antoine Guédon, Pascal Monasse, Vincent Lepetit
We introduce a novel approach to solve the Next Best View problem for dense 3D reconstruction in unknown environments. Contrary to other learning-based methods, our approach scales to large 3D scenes and handles completely free camera motion at inference.
  Paper   Code
                                @inproceedings{guedon2022scone,
                                    title={{SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration}},
                                    author={Gu\'edon, Antoine and Monasse, Pascal and Lepetit, Vincent},
                                    booktitle={{Advances in Neural Information Processing Systems}},
                                    year={2022},
                                  }
                            

© You are welcome to copy the code, please attribute the source with a link back to this page.
Template inspired from Tom Monnier and Mathis Petrovich.