DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912395339759616 |
|---|---|
| author | Huang, Jianxin Li, Jiahang Vityazev, Sergey Dvorkovich, Alexander Fan, Rui |
| author_facet | Huang, Jianxin Li, Jiahang Vityazev, Sergey Dvorkovich, Alexander Fan, Rui |
| contents | RGB-D scene parsing methods effectively capture both semantic and geometric features of the environment, demonstrating great potential under challenging conditions such as extreme weather and low lighting. However, existing RGB-D scene parsing methods predominantly rely on supervised training strategies, which require a large amount of manually annotated pixel-level labels that are both time-consuming and costly. To overcome these limitations, we introduce DepthMatch, a semi-supervised learning framework that is specifically designed for RGB-D scene parsing. To make full use of unlabeled data, we propose complementary patch mix-up augmentation to explore the latent relationships between texture and spatial features in RGB-D image pairs. We also design a lightweight spatial prior injector to replace traditional complex fusion modules, improving the efficiency of heterogeneous feature fusion. Furthermore, we introduce depth-guided boundary loss to enhance the model's boundary prediction capabilities. Experimental results demonstrate that DepthMatch exhibits high applicability in both indoor and outdoor scenes, achieving state-of-the-art results on the NYUv2 dataset and ranking first on the KITTI Semantics benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20041 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization Huang, Jianxin Li, Jiahang Vityazev, Sergey Dvorkovich, Alexander Fan, Rui Computer Vision and Pattern Recognition RGB-D scene parsing methods effectively capture both semantic and geometric features of the environment, demonstrating great potential under challenging conditions such as extreme weather and low lighting. However, existing RGB-D scene parsing methods predominantly rely on supervised training strategies, which require a large amount of manually annotated pixel-level labels that are both time-consuming and costly. To overcome these limitations, we introduce DepthMatch, a semi-supervised learning framework that is specifically designed for RGB-D scene parsing. To make full use of unlabeled data, we propose complementary patch mix-up augmentation to explore the latent relationships between texture and spatial features in RGB-D image pairs. We also design a lightweight spatial prior injector to replace traditional complex fusion modules, improving the efficiency of heterogeneous feature fusion. Furthermore, we introduce depth-guided boundary loss to enhance the model's boundary prediction capabilities. Experimental results demonstrate that DepthMatch exhibits high applicability in both indoor and outdoor scenes, achieving state-of-the-art results on the NYUv2 dataset and ranking first on the KITTI Semantics benchmark. |
| title | DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.20041 |