Arthur is a researcher working on computer vision and machine learning applied to the capture, abstraction, and editing of digital materials.

Prior to joining Adobe, Arthur completed a joint MSc degree in 2014 at ENSAE (statistics, probabilities, finance) and ENS Paris-Saclay (machine learning, vision, applied mathematics). He later conducted applied research during 4 years as a quant in a research-backed finance startup, where he developed a joint love for machine learning deep understanding and the modeling of stochastic processes. Now as part of Adobe Research, he focuses his work on texture representation and synthesis, and the capture and editing of digital materials. When he’s not thinking about visual stochastic processes, Arthur keeps himself busy with hiking, reading SF, and playing piano for fun.

Publications

ControlMat: Controlled Generative Approach to Material Capture

Vecchio, G., Martin, R., Roullier, A., Kaiser, A., ROUFFET, R., Deschaintre, V., Boubekeur, T. (Sep. 1, 2024)

Transaction on Graphics

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

MaterIA: Single Image High-Resolution Material Capture in the Wild

Martin, R., Roullier, A., ROUFFET, R., Kaiser, A., Boubekeur, T. (Apr. 25, 2022)

EUROGRAPHICS 2022