LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911080826011648 |
|---|---|
| author | Zhang, Xiaoyu Pan, Weihong Bao, Chong Zhang, Xiyu Xiang, Xiaojun Jiang, Hanqing Bao, Hujun |
| author_facet | Zhang, Xiaoyu Pan, Weihong Bao, Chong Zhang, Xiyu Xiang, Xiaojun Jiang, Hanqing Bao, Hujun |
| contents | Humans perceive and comprehend their surroundings through information spanning multiple frequencies. In immersive scenes, people naturally scan their environment to grasp its overall structure while examining fine details of objects that capture their attention. However, current NeRF frameworks primarily focus on modeling either high-frequency local views or the broad structure of scenes with low-frequency information, which is limited to balancing both. We introduce FA-NeRF, a novel frequency-aware framework for view synthesis that simultaneously captures the overall scene structure and high-definition details within a single NeRF model. To achieve this, we propose a 3D frequency quantification method that analyzes the scene's frequency distribution, enabling frequency-aware rendering. Our framework incorporates a frequency grid for fast convergence and querying, a frequency-aware feature re-weighting strategy to balance features across different frequency contents. Extensive experiments show that our method significantly outperforms existing approaches in modeling entire scenes while preserving fine details. Project page: https://coscatter.github.io/LookCloser/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18513 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene Zhang, Xiaoyu Pan, Weihong Bao, Chong Zhang, Xiyu Xiang, Xiaojun Jiang, Hanqing Bao, Hujun Computer Vision and Pattern Recognition Humans perceive and comprehend their surroundings through information spanning multiple frequencies. In immersive scenes, people naturally scan their environment to grasp its overall structure while examining fine details of objects that capture their attention. However, current NeRF frameworks primarily focus on modeling either high-frequency local views or the broad structure of scenes with low-frequency information, which is limited to balancing both. We introduce FA-NeRF, a novel frequency-aware framework for view synthesis that simultaneously captures the overall scene structure and high-definition details within a single NeRF model. To achieve this, we propose a 3D frequency quantification method that analyzes the scene's frequency distribution, enabling frequency-aware rendering. Our framework incorporates a frequency grid for fast convergence and querying, a frequency-aware feature re-weighting strategy to balance features across different frequency contents. Extensive experiments show that our method significantly outperforms existing approaches in modeling entire scenes while preserving fine details. Project page: https://coscatter.github.io/LookCloser/ |
| title | LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18513 |