Contour Information Aware 2D Gaussian Splatting for Image Representation
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_ | 1866917173611462656 |
|---|---|
| author | Takabe, Masaya Watanabe, Hiroshi Hong, Sujun Ikai, Tomohiro Fan, Zheming Ishimoto, Ryo Sugimoto, Kakeru Imichi, Ruri |
| author_facet | Takabe, Masaya Watanabe, Hiroshi Hong, Sujun Ikai, Tomohiro Fan, Zheming Ishimoto, Ryo Sugimoto, Kakeru Imichi, Ruri |
| contents | Image representation is a fundamental task in computer vision. Recently, Gaussian Splatting has emerged as an efficient representation framework, and its extension to 2D image representation enables lightweight, yet expressive modeling of visual content. While recent 2D Gaussian Splatting (2DGS) approaches provide compact storage and real-time decoding, they often produce blurry or indistinct boundaries when the number of Gaussians is small due to the lack of contour awareness. In this work, we propose a Contour Information-Aware 2D Gaussian Splatting framework that incorporates object segmentation priors into Gaussian-based image representation. By constraining each Gaussian to a specific segmentation region during rasterization, our method prevents cross-boundary blending and preserves edge structures under high compression. We also introduce a warm-up scheme to stabilize training and improve convergence. Experiments on synthetic color charts and the DAVIS dataset demonstrate that our approach achieves higher reconstruction quality around object edges compared to existing 2DGS methods. The improvement is particularly evident in scenarios with very few Gaussians, while our method still maintains fast rendering and low memory usage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23255 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contour Information Aware 2D Gaussian Splatting for Image Representation Takabe, Masaya Watanabe, Hiroshi Hong, Sujun Ikai, Tomohiro Fan, Zheming Ishimoto, Ryo Sugimoto, Kakeru Imichi, Ruri Computer Vision and Pattern Recognition Image representation is a fundamental task in computer vision. Recently, Gaussian Splatting has emerged as an efficient representation framework, and its extension to 2D image representation enables lightweight, yet expressive modeling of visual content. While recent 2D Gaussian Splatting (2DGS) approaches provide compact storage and real-time decoding, they often produce blurry or indistinct boundaries when the number of Gaussians is small due to the lack of contour awareness. In this work, we propose a Contour Information-Aware 2D Gaussian Splatting framework that incorporates object segmentation priors into Gaussian-based image representation. By constraining each Gaussian to a specific segmentation region during rasterization, our method prevents cross-boundary blending and preserves edge structures under high compression. We also introduce a warm-up scheme to stabilize training and improve convergence. Experiments on synthetic color charts and the DAVIS dataset demonstrate that our approach achieves higher reconstruction quality around object edges compared to existing 2DGS methods. The improvement is particularly evident in scenarios with very few Gaussians, while our method still maintains fast rendering and low memory usage. |
| title | Contour Information Aware 2D Gaussian Splatting for Image Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.23255 |