My picture

Valentin Deschaintre

Research Scientist - Adobe Research
Google scholar Github Linkedin D19 Mastodon

I am currently a Research Scientist at Adobe Research in the London lab. I previously was an Associate Researcher in the Realistic Graphics and Imaging group of Imperial College London hosted by Abhijeet Ghosh. I received my PhD at Inria Sophia-Antipolis from the GraphDeco research group under the supervision of Adrien Bousseau and George Drettakis in collaboration with Optis, an Ansys affiliate. During my PhD, I spent 2 months in MIT under the supervision of Frédo Durand, at MIT CSAIL.
My Thesis received the French Computer Graphics Thesis Award and UCA Academic Excellence Thesis Awards. I was elected as one of the Eurographics Junior Fellow 2024.
My research focuses on inverse rendering, with a special focus on generation, acquisition, creation, editing and representation for virtual environments.

Internships

Adobe Research Internship: I will be looking for strong PhD students to collaborate with for the 2025 Adobe internship program. If you are interested in interning at Adobe with me (see my research interests above), don't hesitate to reach out (deschain@a***e.com) detailing what your research interests are, and what you would like to work on during the internship. Internships are usually discussed around November December of the year preceding it. It is important that your advisor is aware of your plans to do an intership.

Past Interns

In recent years, I was happy to collaborate with great students in the context of Adobe's PhD Internship program!

Publications

TexSliders: Diffusion-Based Texture Editing in CLIP Space. Julia Guerrero-Viu, Miloš Hašan, Arthur Roullier, Midhun Harikumar, Yiwei Hu, Paul Guerrero, Diego Gutierrez, Belen Masia, Valentin Deschaintre, Siggraph 2024

RGB↔X: Image Decomposition and Synthesis Using Material- and Lighting-aware Diffusion Models. Zheng Zeng, Valentin Deschaintre, Iliyan Georgiev, Yannick Hold-Geoffroy, Yiwei Hu, Fujun Luan, Ling-Qi Yan, Miloš Hašan, Siggraph 2024

MeshLRM: Large Reconstruction Model for High-Quality Meshes. Xinyue Wei*, Kai Zhang*, Sai Bi, Hao Tan, Fujun Luan, Valentin Deschaintre, Kalyan Sunkavalli, Hao Su, Zexiang Xu, Arxiv 2024

MatAtlas: Text-driven Consistent Geometry Texturing and Material Assignment. Duygu Ceylan, Valentin Deschaintre, Thibault Groueix, Rosalie Martin, Chun-Hao Huang, Romain Rouffet, Vladimir Kim, Gaëtan Lassagne, Arxiv 2024

MatSynth: A Modern PBR Materials Dataset. Giuseppe Vecchio, Valentin Deschaintre, CVPR 2024

ControlMat: Controlled Generative Approach to Material Capture. Giuseppe Vecchio, Rosalie Martin, Arthur Roullier, Adrien Kaiser, Romain Rouffet, Valentin Deschaintre, Tamy Boubekeur, Arxiv 2023

PSDR-Room: Single Photo to Scene using Differentiable Rendering. Kai Yan, Fujun Luan, Milos Hasan, Thibault Groueix, Valentin Deschaintre, Shuang Zhao, Siggraph Asia, 2023

Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training. Julien Philip, Valentin Deschaintre, EGSR, 2023

Materialistic: Selecting Similar Materials in Images. Prafull Sharma, Julien Philip, Michael Gharbi, Bill Freeman, Fredo Durand, Valentin Deschaintre, Transactions on Graphics (Siggraph proc.) 2023

Generating Procedural Materials from Text or Image Prompts. Yiwei Hu, Paul Guerrero, Miloš Hašan, Holly Rushmeier, Valentin Deschaintre, Siggraph, 2023

The Visual Language of Fabrics. Valentin Deschaintre*, Julia Guerrero-Viu*, Diego Gutierrez, Tamy Boubekeur, Belen Masia, Transactions on Graphics (Siggraph proc.) 2023

PhotoMat: A Material Generator Learned from Single Flash Photos. Xilong Zhou, Miloš Hašan, Valentin Deschaintre, Paul Guerrero, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Nima Kalantari, Siggraph, 2023

A Semi‐Procedural Convolutional Material Prior. Xilong Zhou, Miloš Hašan, Valentin Deschaintre, Paul Guerrero, Kalyan Sunkavalli, Nima Kalantari, CGF, 2023

TileGen: Tileable, Controllable Material Generation and Capture. Xilong Zhou, Miloš Hašan, Valentin Deschaintre, Paul Guerrero, Kalyan Sunkavalli, Nima Kalantari, Siggraph Asia 2022

Node Graph Optimization Using Differentiable Proxies. Yiwei Hu, Paul Guerrero, Miloš Hašan, Holly Rushmeier, Valentin Deschaintre, Siggraph, August 2022

Controlling Material Appearance by Examples. Yiwei Hu, Miloš Hašan, Paul Guerrero, Holly Rushmeier, Valentin Deschaintre, Computer Graphics Forum (Eurographics Symposium on Rendering Conference Proceedings), July 2022

Spectral Upsampling Approaches for RGB Illumination. Claudio Giuseppe Guarnera, Yuliya Gitlina, Valentin Deschaintre, Abhijeet Ghosh, Eurographics Symposium on Rendering - Symposium Track, July 2022

An Inverse Procedural Modeling Pipeline for SVBRDF Maps. Yiwei Hu, Chengan He, Valentin Deschaintre, Julie Dorsey, Holly Rushmeier, ACM Trans Graph, April 2022 (Presented at SIGGRAPH 2022)

Generative Modelling of BRDF Textures from Flash Images. Philipp Henzler, Valentin Deschaintre, Niloy J. Mitra, Tobias Ritschel, ACM Trans Graph (Proc. SIGGRAPH Asia 2021)

  • Our paper was accepted as CVPR Oral.
Deep polarization imaging for 3D shape and SVBRDF acquisition. Valentin Deschaintre, Yiming Lin, and Abhijeet Ghosh. Proc. of CVPR, June 2021. (Patent Pending)

Computer Graphics Forum (Eurographics Symposium on Rendering Conference Proceedings), Volume 39, Number 4 - jul 2020

Université Côté d'Azur, Inria, PhD Thesis, Nov 2019

Asia, Doctoral Consortium (Poster and Short Paper), Nov 2019

Computer Graphics Forum (Eurographics Symposium on Rendering Conference Proceedings), Volume 38, Number 4, page 13 - jul 2019

ACM Transactions on Graphics (SIGGRAPH Conference Proceedings), Volume 37, Number 128, page 15 - aug 2018

Community activities