DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation
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_ | 1866911078373392384 |
|---|---|
| author | Cho, Suhwan Lee, Minhyeok Lee, Jungho Kim, Donghyeong Lee, Sangyoun |
| author_facet | Cho, Suhwan Lee, Minhyeok Lee, Jungho Kim, Donghyeong Lee, Sangyoun |
| contents | Unsupervised video object segmentation (VOS) aims to detect the most prominent object in a video. Recently, two-stream approaches that leverage both RGB images and optical flow have gained significant attention, but their performance is fundamentally constrained by the scarcity of training data. To address this, we propose DepthFlow, a novel data generation method that synthesizes optical flow from single images. Our approach is driven by the key insight that VOS models depend more on structural information embedded in flow maps than on their geometric accuracy, and that this structure is highly correlated with depth. We first estimate a depth map from a source image and then convert it into a synthetic flow field that preserves essential structural cues. This process enables the transformation of large-scale image-mask pairs into image-flow-mask training pairs, dramatically expanding the data available for network training. By training a simple encoder-decoder architecture with our synthesized data, we achieve new state-of-the-art performance on all public VOS benchmarks, demonstrating a scalable and effective solution to the data scarcity problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19790 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation Cho, Suhwan Lee, Minhyeok Lee, Jungho Kim, Donghyeong Lee, Sangyoun Computer Vision and Pattern Recognition Unsupervised video object segmentation (VOS) aims to detect the most prominent object in a video. Recently, two-stream approaches that leverage both RGB images and optical flow have gained significant attention, but their performance is fundamentally constrained by the scarcity of training data. To address this, we propose DepthFlow, a novel data generation method that synthesizes optical flow from single images. Our approach is driven by the key insight that VOS models depend more on structural information embedded in flow maps than on their geometric accuracy, and that this structure is highly correlated with depth. We first estimate a depth map from a source image and then convert it into a synthetic flow field that preserves essential structural cues. This process enables the transformation of large-scale image-mask pairs into image-flow-mask training pairs, dramatically expanding the data available for network training. By training a simple encoder-decoder architecture with our synthesized data, we achieve new state-of-the-art performance on all public VOS benchmarks, demonstrating a scalable and effective solution to the data scarcity problem. |
| title | DepthFlow: Exploiting Depth-Flow Structural Correlations for Unsupervised Video Object Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19790 |