Clément Jambon

I am currently studying at ETH Zürich, where I follow a master of science. Among the Computer Science Department, I am majoring in Visual and Interactive Computing and minoring in Machine Learning. Additionally, I am a fourth-year engineering student at École polytechnique in Paris.

I have recently completed a five-month research internship at Inria Sophia-Antipolis in the GraphDeco team. There, I was supervised by George Drettakis and kindly advised by Georgios Kopanas, Stavros Diolatzis and Thomas Leimkühler. My work was mostly focused on point-based neural rendering and Neural Radiance Fields a.k.a. NeRF. This resulted in a contribution to Neural Point Catacaustics released at SIGGRAPH ASIA 2022 and NeRFshop, a personal publication to be presented at I3D 2023.

I am interested in computer vision, computer graphics and their connections with machine learning. Most notably, I am currently focusing on topics such as neural rendering, diffusion models and neural fields. Some of my recent interests also include neuro-symbolic AI and machine perception.

Email  /  Scholar  /  CV  /  Twitter  /  Github  /  LinkedIn

profile photo
logo-ethz ETH Zürich
Department of Computer Science
Master of Science
Major in Visual and Interactive Computing
September 2022 - current
logo-polytechnique École polytechnique
Department of Computer Science
Postgraduate engineering degree
Major in Image, Vision and Learning
September 2019 - August 2023
NeRFshop: Interactive Editing of Neural Radiance Fields
Clément Jambon, Bernhard Kerbl, Georgios Kopanas,
Stavros Diolatzis, Thomas Leimkühler, George Drettakis
I3D, 2023
project page / pre-print / video

NeRFshop is a novel end-to-end method that allows users to interactively select and deform objects through cage-based transformations. Once complete, edits can be collapsed and saved as a portable NeRF representation through a distillation process.

Neural Point Catacaustics for Novel-View Synthesis of Reflections
Georgios Kopanas, Thomas Leimkühler, Gilles Reiner,
Clément Jambon, George Drettakis
project page / pre-print / video

We introduce a new point-based representation to compute Neural Point Catacaustics allowing novel-view synthesis of scenes with curved reflectors, from a set of casually-captured input.

This website was made with Jon Barron's template.