DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRF
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918115590275072 |
|---|---|
| author | Lee, Ingyun Jang, Jae Won Seo, Seunghyeon Kwak, Nojun |
| author_facet | Lee, Ingyun Jang, Jae Won Seo, Seunghyeon Kwak, Nojun |
| contents | Neural Radiance Field (NeRF) has shown remarkable performance in novel view synthesis but requires numerous multi-view images, limiting its practicality in few-shot scenarios. Ray augmentation has been proposed to alleviate overfitting caused by sparse training data by generating additional rays. However, existing methods, which generate augmented rays only near the original rays, exhibit pronounced floaters and appearance distortions due to limited viewpoints and inconsistent rays obstructed by nearby obstacles and complex surfaces. To address these problems, we propose DivCon-NeRF, which introduces novel sphere-based ray augmentations to significantly enhance both diversity and consistency. By employing a virtual sphere centered at the predicted surface point, our method generates diverse augmented rays from all 360-degree directions, facilitated by our consistency mask that effectively filters out inconsistent rays. We introduce tailored loss functions that leverage these augmentations, effectively reducing floaters and visual distortions. Consequently, our method outperforms existing few-shot NeRF approaches on the Blender, LLFF, and DTU datasets. Furthermore, DivCon-NeRF demonstrates strong generalizability by effectively integrating with both regularization- and framework-based few-shot NeRFs. Our code will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRF Lee, Ingyun Jang, Jae Won Seo, Seunghyeon Kwak, Nojun Computer Vision and Pattern Recognition Neural Radiance Field (NeRF) has shown remarkable performance in novel view synthesis but requires numerous multi-view images, limiting its practicality in few-shot scenarios. Ray augmentation has been proposed to alleviate overfitting caused by sparse training data by generating additional rays. However, existing methods, which generate augmented rays only near the original rays, exhibit pronounced floaters and appearance distortions due to limited viewpoints and inconsistent rays obstructed by nearby obstacles and complex surfaces. To address these problems, we propose DivCon-NeRF, which introduces novel sphere-based ray augmentations to significantly enhance both diversity and consistency. By employing a virtual sphere centered at the predicted surface point, our method generates diverse augmented rays from all 360-degree directions, facilitated by our consistency mask that effectively filters out inconsistent rays. We introduce tailored loss functions that leverage these augmentations, effectively reducing floaters and visual distortions. Consequently, our method outperforms existing few-shot NeRF approaches on the Blender, LLFF, and DTU datasets. Furthermore, DivCon-NeRF demonstrates strong generalizability by effectively integrating with both regularization- and framework-based few-shot NeRFs. Our code will be made publicly available. |
| title | DivCon-NeRF: Diverse and Consistent Ray Augmentation for Few-Shot NeRF |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12947 |