Few-shot NeRF by Adaptive Rendering Loss Regularization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909360387522560 |
|---|---|
| author | Xu, Qingshan Yi, Xuanyu Xu, Jianyao Tao, Wenbing Ong, Yew-Soon Zhang, Hanwang |
| author_facet | Xu, Qingshan Yi, Xuanyu Xu, Jianyao Tao, Wenbing Ong, Yew-Soon Zhang, Hanwang |
| contents | Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF). Recent works demonstrate that the frequency regularization of Positional Encoding (PE) can achieve promising results for few-shot NeRF. In this work, we reveal that there exists an inconsistency between the frequency regularization of PE and rendering loss. This prevents few-shot NeRF from synthesizing higher-quality novel views. To mitigate this inconsistency, we propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF. Specifically, we present a two-phase rendering supervision and an adaptive rendering loss weight learning strategy to align the frequency relationship between PE and 2D-pixel supervision. In this way, AR-NeRF can learn global structures better in the early training phase and adaptively learn local details throughout the training process. Extensive experiments show that our AR-NeRF achieves state-of-the-art performance on different datasets, including object-level and complex scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17839 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Few-shot NeRF by Adaptive Rendering Loss Regularization Xu, Qingshan Yi, Xuanyu Xu, Jianyao Tao, Wenbing Ong, Yew-Soon Zhang, Hanwang Computer Vision and Pattern Recognition Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF). Recent works demonstrate that the frequency regularization of Positional Encoding (PE) can achieve promising results for few-shot NeRF. In this work, we reveal that there exists an inconsistency between the frequency regularization of PE and rendering loss. This prevents few-shot NeRF from synthesizing higher-quality novel views. To mitigate this inconsistency, we propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF. Specifically, we present a two-phase rendering supervision and an adaptive rendering loss weight learning strategy to align the frequency relationship between PE and 2D-pixel supervision. In this way, AR-NeRF can learn global structures better in the early training phase and adaptively learn local details throughout the training process. Extensive experiments show that our AR-NeRF achieves state-of-the-art performance on different datasets, including object-level and complex scenes. |
| title | Few-shot NeRF by Adaptive Rendering Loss Regularization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.17839 |