Skip to Main content Skip to Navigation
New interface

Lightweight material acquisition using deep learning

Valentin Deschaintre 1 
1 GRAPHDECO - GRAPHics and DEsign with hEterogeneous COntent
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Whether it is used for entertainment or industrial design, computer graphics is ever more present in our everyday life. Yet, reproducing a real scene appearance in a virtual environment remains a challenging task, requiring long hours from trained artists. A good solution is the acquisition of geometries and materials directly from real world examples, but this often comes at the cost of complex hardware and calibration processes. In this thesis, we focus on lightweight material appearance capture to simplify and accelerate the acquisition process and solve industrial challenges such as result image resolution or calibration. Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in pictures. Designing algorithms able to leverage these cues to recover spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a few images has challenged computer graphics researchers for decades. We explore the use of deep learning to tackle lightweight appearance capture and make sense of these visual cues. Once trained, our networks are capable of recovering per-pixel normals, diffuse albedo, specular albedo and specular roughness from as little as one picture of a flat surface lit by the environment or a hand-held flash. We show how our method improves its prediction with the number of input pictures to reach high quality reconstructions with up to 10 images --- a sweet spot between existing single-image and complex multi-image approaches --- and allows to capture large scale, HD materials. We achieve this goal by introducing several innovations on training data acquisition and network design, bringing clear improvement over the state of the art for lightweight material capture.
Document type :
Complete list of metadata

Cited literature [105 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Thursday, June 25, 2020 - 9:51:14 AM
Last modification on : Saturday, June 25, 2022 - 11:46:00 PM


Version validated by the jury (STAR)


  • HAL Id : tel-02418445, version 2



Valentin Deschaintre. Lightweight material acquisition using deep learning. Image Processing [eess.IV]. COMUE Université Côte d'Azur (2015 - 2019), 2019. English. ⟨NNT : 2019AZUR4078⟩. ⟨tel-02418445v2⟩



Record views


Files downloads