Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2603.03718 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908865353744384 |
|---|---|
| author | Ojala, Risto Ellison, Tristan Chen, Mo |
| author_facet | Ojala, Risto Ellison, Tristan Chen, Mo |
| contents | Glass surface segmentation from RGB images is a challenging task, since glass as a transparent material distinctly lacks visual characteristics. However, glass segmentation is critical for scene understanding and robotics, as transparent glass surfaces must be identified as solid material. This paper presents a novel architecture for glass segmentation, deploying a dual-backbone producing general visual features as well as task-specific learned visual features. General visual features are produced by a frozen DINOv3 vision foundation model, and the task-specific features are generated with a Swin model trained in a supervised manner. Resulting multi-scale feature representations are downsampled with residual Squeeze-and-Excitation Channel Reduction, and fed into a Mask2Former Decoder, producing the final segmentation masks. The architecture was evaluated on four commonly used glass segmentation datasets, achieving state-of-the-art results on several accuracy metrics. The model also has a competitive inference speed compared to the previous state-of-the-art method, and surpasses it when using a lighter DINOv3 backbone variant. The implementation source code and model weights are available at: https://github.com/ojalar/lgnet |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03718 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Glass Segmentation with Fusion of Learned and General Visual Features Ojala, Risto Ellison, Tristan Chen, Mo Computer Vision and Pattern Recognition Glass surface segmentation from RGB images is a challenging task, since glass as a transparent material distinctly lacks visual characteristics. However, glass segmentation is critical for scene understanding and robotics, as transparent glass surfaces must be identified as solid material. This paper presents a novel architecture for glass segmentation, deploying a dual-backbone producing general visual features as well as task-specific learned visual features. General visual features are produced by a frozen DINOv3 vision foundation model, and the task-specific features are generated with a Swin model trained in a supervised manner. Resulting multi-scale feature representations are downsampled with residual Squeeze-and-Excitation Channel Reduction, and fed into a Mask2Former Decoder, producing the final segmentation masks. The architecture was evaluated on four commonly used glass segmentation datasets, achieving state-of-the-art results on several accuracy metrics. The model also has a competitive inference speed compared to the previous state-of-the-art method, and surpasses it when using a lighter DINOv3 backbone variant. The implementation source code and model weights are available at: https://github.com/ojalar/lgnet |
| title | Glass Segmentation with Fusion of Learned and General Visual Features |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03718 |