Abstract | ||
---|---|---|
Dense 3D face reconstruction plays a fundamental role in visual media production involving digital actors. We improve upon high fidelity reconstruction from a single 2D photo with a reconstruction framework that is robust to large variations in expressions, poses and illumination. We provide a global optimization step improving the alignment of 3D facial geometry to tracked 2D landmarks with 3D Laplacian deformation. Face detail is improved through, extending Shape from Shading reconstruction with fitted albedo prior masks, together with a fast proportionality constraint between depth and image gradients consistent with local self-occlusion behavior. Together these measures better preserve the crucial facial features that define an actor's identity, and we illustrate this through a variety of comparisons with related works. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3278471.3278473 | PROCEEDINGS CVMP 2018: THE 15TH ACM SIGGRAPH EUROPEAN CONFERENCE ON VISUAL MEDIA PRODUCTION |
Keywords | Field | DocType |
Feature-Preserving, Reconstruction, Optimization | High fidelity,Computer vision,Facial geometry,Expression (mathematics),Computer graphics (images),Global optimization,Computer science,Albedo,Artificial intelligence,Visual media,Photometric stereo,Laplace operator | Conference |
Citations | PageRank | References |
2 | 0.36 | 19 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yue Li | 1 | 133 | 42.96 |
Li-Qian Ma | 2 | 99 | 5.70 |
Haoqiang Fan | 3 | 8 | 3.13 |
Kenny Mitchell | 4 | 216 | 23.95 |