Valentin Deschaintre

Research Scientist

London

Valentin Deschaintre is a Research Scientist at Adobe. Previously, he was an Associate Researcher in the Realistic Graphics and Imaging group of Imperial College London hosted by Abhijeet Ghosh. He obtained his PhD from Inria, in the GraphDeco research group, under the supervision of Adrien Bousseau and George Drettakis. During his PhD he spent 2 months under the supervision of Frédo Durand, at MIT CSAIL.

His research focuses on material and shape acquisition, creation and representation, leveraging deep learning methods. More information is available on his website.

Publications

RGB<->X: Image Decomposition and Synthesis Using Material- and Lighting-aware Diffusion Models

Zeng, Z., Deschaintre, V., Georgiev, I., Hold-Geoffroy, Y., Hu, Y., Luan, F., Yan, L., Hasan, M. (Jul. 25, 2024)

SIGGRAPH 2024

TexSliders: Diffusion-Based Texture Editing in CLIP Space

Guerrero-Viu, J., Hasan, M., Roullier, A., Harikumar, M., Hu, Y., Guerrero, P., Gutierrez, D., Masia, B., Deschaintre, V. (Jul. 25, 2024)

SIGGRAPH 2024

MatSynth: A Modern PBR Materials Dataset

Vecchio, G., Deschaintre, V. (Jun. 25, 2024)

CVPR 2024

PSDR-Room: Single Photo to Scene using Differentiable Rendering

Yan, K., Luan, F., Hasan, M., Groueix, T., Deschaintre, V., Zhao, S. (Dec. 1, 2023)

Siggraph Asia 2023

PhotoMat: A Material Generator Learned from Single Flash Photos

Zhou, X., Hašan, M., Deschaintre, V., Guerrero, P., Hold-Geoffroy, Y., Sunkavalli, K., Kalantari, N. (Aug. 1, 2023)

Siggraph 2023

Materialistic: Selecting Similar Materials in Images

Sharma, P., Philip, J., Gharbi, M., Freeman, W., Durand, F., Deschaintre, V. (Aug. 1, 2023)

Siggraph 2023

The Visual Language of Fabrics

Deschaintre, V., Guerrero-Viu, J., Gutierrez, D., Boubekeur, T., Masia, B. (Aug. 1, 2023)

Siggraph 2023

Generating Procedural Materials from Text or Image Prompts

Hu, Y., Guerrero, P., Hašan, M., Rushmeier, H., Deschaintre, V. (Aug. 1, 2023)

Siggraph 2023

Floaters No More: Radiance Field Gradient Scaling for Improved Near-Camera Training

Philip, J., Deschaintre, V. (Jul. 1, 2023)

EGSR 2023

A Semi-Procedural Convolutional Material Prior

Zhou, X., Hašan, M., Deschaintre, V., Guerrero, P., Sunkavalli, K., Kalantari, N. (Mar. 10, 2023)

CGF, Eurographics 2023

TileGen: Tileable, Controllable Material Generation and Capture

Zhou, X., Hašan, M., Deschaintre, V., Guerrero, P., Sunkavalli, K., Kalantari, N. (Dec. 1, 2022)

Siggraph Asia 2022

Node Graph Optimization Using Differentiable Proxies

Hu, Y., Guerrero, P., Hašan, M., Rushmeier, H., Deschaintre, V. (Aug. 1, 2022)

Siggraph 2022

Controlling Material Appearance by Examples

Hu, Y., Hašan, M., Guerrero, P., Rushmeier, H., Deschaintre, V. (Jul. 1, 2022)

Computer Graphics Forum (EGSR 2022)

Generative Modelling of BRDF Textures from Flash Images

Henzler, P., Deschaintre, V., Mitra, N., Ritschel, T. (Dec. 17, 2021)

Siggraph Asia 2021

An Inverse Procedural Modeling Pipeline for SVBRDF Maps

Hu, Y., He, C., Deschaintre, V., Dorsey, J., Rushmeier, H. (Dec. 15, 2021)

Transaction On Graphics (TOG), Siggraph 2022