Lightweight material acquisition using deep learning

Simple item page
dc.contributor.authorDeschaintre, Valentin
dc.date.accessioned2020-11-25T09:34:56Z
dc.date.available2020-11-25T09:34:56Z
dc.date.issued2019-11
dc.description.abstractWhether 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.en_US
dc.identifier.citationValentin Deschaintre. Lightweight material acquisition using deep learning. Computer Science [cs]. Université côte d'azur; Inria - Sophia Antipolis, 2019. English. ⟨tel-02418445v1⟩en_US
dc.identifier.other2019AZUR4078
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/2632983
dc.language.isoenen_US
dc.subjectMaterial acquisitionen_US
dc.subjectDeep learningen_US
dc.titleLightweight material acquisition using deep learningen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Lightweight Material Acquisition Using Deep Learning Deschaintre.pdf
Size:
70.13 MB
Format:
Adobe Portable Document Format
Description:
Lightweight material acquisition using deep learning Thesis, Valentin Deschaintre
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.79 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
2019