Deep Polarization Imaging for 3D shape and SVBRDF Acquisition

no code implementations • CVPR 2021 • Valentin Deschaintre, Yiming Lin, Abhijeet Ghosh

We present a novel method for efficient acquisition of shape and spatially varying reflectance of 3D objects using polarization cues.

Generative Modelling of BRDF Textures from Flash Images

no code implementations • 23 Feb 2021 • Philipp Henzler, Valentin Deschaintre, Niloy J. Mitra, Tobias Ritschel

We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance.

Guided Fine-Tuning for Large-Scale Material Transfer

1 code implementation • 6 Jul 2020 • Valentin Deschaintre, George Drettakis, Adrien Bousseau

Our solution is extremely simple: we fine-tune a deep appearance-capture network on the provided exemplars, such that it learns to extract similar SVBRDF values from the target image.

Flexible SVBRDF Capture with a Multi-Image Deep Network

1 code implementation • 27 Jun 2019 • Valentin Deschaintre, Miika Aittala, Fredo Durand, George Drettakis, Adrien Bousseau

Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph.

Graphics I.3

Single-Image SVBRDF Capture with a Rendering-Aware Deep Network

1 code implementation • 23 Oct 2018 • Valentin Deschaintre, Miika Aittala, Fredo Durand, George Drettakis, Adrien Bousseau

Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures.

Graphics I.3