VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917992285077504 |
|---|---|
| author | Lin, Lifeng Lu, Rongfeng Chen, Quan Ren, Haofan Lu, Ming Sun, Yaoqi Yan, Chenggang Xue, Anke |
| author_facet | Lin, Lifeng Lu, Rongfeng Chen, Quan Ren, Haofan Lu, Ming Sun, Yaoqi Yan, Chenggang Xue, Anke |
| contents | Sparse-view 3D reconstruction is a fundamental yet challenging task in practical 3D reconstruction applications. Recently, many methods based on the 3D Gaussian Splatting (3DGS) framework have been proposed to address sparse-view 3D reconstruction. Although these methods have made considerable advancements, they still show significant issues with overfitting. To reduce the overfitting, we introduce VGNC, a novel Validation-guided Gaussian Number Control (VGNC) approach based on generative novel view synthesis (NVS) models. To the best of our knowledge, this is the first attempt to alleviate the overfitting issue of sparse-view 3DGS with generative validation images. Specifically, we first introduce a validation image generation method based on a generative NVS model. We then propose a Gaussian number control strategy that utilizes generated validation images to determine the optimal Gaussian numbers, thereby reducing the issue of overfitting. We conducted detailed experiments on various sparse-view 3DGS baselines and datasets to evaluate the effectiveness of VGNC. Extensive experiments show that our approach not only reduces overfitting but also improves rendering quality on the test set while decreasing the number of Gaussian points. This reduction lowers storage demands and accelerates both training and rendering. The code will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14548 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control Lin, Lifeng Lu, Rongfeng Chen, Quan Ren, Haofan Lu, Ming Sun, Yaoqi Yan, Chenggang Xue, Anke Computer Vision and Pattern Recognition Artificial Intelligence Sparse-view 3D reconstruction is a fundamental yet challenging task in practical 3D reconstruction applications. Recently, many methods based on the 3D Gaussian Splatting (3DGS) framework have been proposed to address sparse-view 3D reconstruction. Although these methods have made considerable advancements, they still show significant issues with overfitting. To reduce the overfitting, we introduce VGNC, a novel Validation-guided Gaussian Number Control (VGNC) approach based on generative novel view synthesis (NVS) models. To the best of our knowledge, this is the first attempt to alleviate the overfitting issue of sparse-view 3DGS with generative validation images. Specifically, we first introduce a validation image generation method based on a generative NVS model. We then propose a Gaussian number control strategy that utilizes generated validation images to determine the optimal Gaussian numbers, thereby reducing the issue of overfitting. We conducted detailed experiments on various sparse-view 3DGS baselines and datasets to evaluate the effectiveness of VGNC. Extensive experiments show that our approach not only reduces overfitting but also improves rendering quality on the test set while decreasing the number of Gaussian points. This reduction lowers storage demands and accelerates both training and rendering. The code will be released. |
| title | VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.14548 |