Name
Title | ||
|---|---|---|
Modeling surface appearance from a single photograph using self-augmented convolutional neural networks |
Abstract | ||
|---|---|---|
We present a convolutional neural network (CNN) based solution for modeling physically plausible spatially varying surface reflectance functions (SVBRDF) from a single photograph of a planar material sample under unknown natural illumination. Gathering a sufficiently large set of labeled training pairs consisting of photographs of SVBRDF samples and corresponding reflectance parameters, is a difficult and arduous process. To reduce the amount of required labeled training data, we propose to leverage the appearance information embedded in unlabeled images of spatially varying materials to self-augment the training process. Starting from an initial approximative network obtained from a small set of labeled training pairs, we estimate provisional model parameters for each unlabeled training exemplar. Given this provisional reflectance estimate, we then synthesize a novel temporary labeled training pair by rendering the exact corresponding image under a new lighting condition. After refining the network using these additional training samples, we re-estimate the provisional model parameters for the unlabeled data and repeat the self-augmentation process until convergence. We demonstrate the efficacy of the proposed network structure on spatially varying wood, metals, and plastics, as well as thoroughly validate the effectiveness of the self-augmentation training process. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1145/3072959.3073641 | ACM Trans. Graph. |
Keywords | DocType | Volume |
Appearance Modeling,SVBRDF,CNN | Journal | 36 |
Issue | ISSN | Citations |
4 | 0730-0301 | 25 |
PageRank | References | Authors |
0.79 | 21 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiao Li | 1 | 46 | 3.06 |
| Yue Dong | 2 | 428 | 25.42 |
| Pieter Peers | 3 | 1109 | 55.34 |
| Xin Tong | 4 | 2119 | 127.72 |