DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering
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_ | 1866916687923642368 |
|---|---|
| author | Xu, Yexing Wang, Longguang Chen, Minglin Ao, Sheng Li, Li Guo, Yulan |
| author_facet | Xu, Yexing Wang, Longguang Chen, Minglin Ao, Sheng Li, Li Guo, Yulan |
| contents | Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09491 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering Xu, Yexing Wang, Longguang Chen, Minglin Ao, Sheng Li, Li Guo, Yulan Computer Vision and Pattern Recognition Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/. |
| title | DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.09491 |