Name
Abstract | ||
|---|---|---|
Stereo matching is an important problem in computer vision which has drawn tremendous research attention for decades. Recent years, data-driven methods with convolutional neural networks (CNNs) are continuously pushing stereo matching to new heights. However, data-driven methods require large amount of training data, which is not an easy task for real stereo data due to the annotation difficulties of per-pixel ground-truth disparity. Though synthetic dataset is proposed to fill the gaps of large data demand, the fine-tuning on real dataset is still needed due to the domain variances between synthetic data and real data. In this paper, we found that in synthetic datasets, close-to-real-scene texture rendering is a key factor to boost up stereo matching performance, while close-to-real-scene 3D modeling is less important. We then propose semi-synthetic, an effective and fast way to synthesize large amount of data with close-to-real-scene texture to minimize the gap between synthetic data and real data. Extensive experiments demonstrate that models trained with our proposed semi-synthetic datasets achieve significantly better performance than with general synthetic datasets, especially on real data benchmarks with limited training data. With further fine-tuning on the real dataset, we also achieve SOTA performance on Middlebury and competitive results on KITTI and ETH3D datasets. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPRW53098.2021.00323 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ju He | 1 | 4 | 3.43 |
| Enyu Zhou | 2 | 0 | 0.68 |
| Liusheng Sun | 3 | 0 | 0.34 |
| Fei Lei | 4 | 0 | 0.34 |
| Chenyang Liu | 5 | 0 | 0.34 |
| Wenxiu Sun | 6 | 0 | 0.34 |