See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916574412144640 |
|---|---|
| author | He, Zongqi Xiao, Zhe Chan, Kin-Chung Zuo, Yushen Xiao, Jun Lam, Kin-Man |
| author_facet | He, Zongqi Xiao, Zhe Chan, Kin-Chung Zuo, Yushen Xiao, Jun Lam, Kin-Man |
| contents | 3D Gaussian Splatting (3DGS) has shown remarkable performance in novel view synthesis. However, its rendering quality deteriorates with sparse inphut views, leading to distorted content and reduced details. This limitation hinders its practical application. To address this issue, we propose a sparse-view 3DGS method. Given the inherently ill-posed nature of sparse-view rendering, incorporating prior information is crucial. We propose a semantic regularization technique, using features extracted from the pretrained DINO-ViT model, to ensure multi-view semantic consistency. Additionally, we propose local depth regularization, which constrains depth values to improve generalization on unseen views. Our method outperforms state-of-the-art novel view synthesis approaches, achieving up to 0.4dB improvement in terms of PSNR on the LLFF dataset, with reduced distortion and enhanced visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11508 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization He, Zongqi Xiao, Zhe Chan, Kin-Chung Zuo, Yushen Xiao, Jun Lam, Kin-Man Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) has shown remarkable performance in novel view synthesis. However, its rendering quality deteriorates with sparse inphut views, leading to distorted content and reduced details. This limitation hinders its practical application. To address this issue, we propose a sparse-view 3DGS method. Given the inherently ill-posed nature of sparse-view rendering, incorporating prior information is crucial. We propose a semantic regularization technique, using features extracted from the pretrained DINO-ViT model, to ensure multi-view semantic consistency. Additionally, we propose local depth regularization, which constrains depth values to improve generalization on unseen views. Our method outperforms state-of-the-art novel view synthesis approaches, achieving up to 0.4dB improvement in terms of PSNR on the LLFF dataset, with reduced distortion and enhanced visual quality. |
| title | See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.11508 |