Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.21226 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911364814995456 |
|---|---|
| author | Lavi, Yishai Segre, Leo Avidan, Shai |
| author_facet | Lavi, Yishai Segre, Leo Avidan, Shai |
| contents | 3D Gaussian Splatting (3D-GS) enables efficient novel view synthesis, but treats all frequencies uniformly, making it difficult to separate coarse structure from fine detail. Recent works have started to exploit frequency signals, but lack explicit frequency decomposition of the 3D representation itself. We propose a frequency-aware decomposition that organizes 3D Gaussians into groups corresponding to Laplacian-pyramid subbands of the input images. Each group is trained with spatial frequency regularization to confine it to its target frequency, while higher-frequency bands use signed residual colors to capture fine details that may be missed by lower-frequency reconstructions. A progressive coarse-to-fine training schedule stabilizes the decomposition. Our method achieves state-of-the-art reconstruction quality and rendering speed among all LOD-capable methods. In addition to improved interpretability, our method enables dynamic level-of-detail rendering, progressive streaming, foveated rendering, promptable 3D focus, and artistic filtering. Our code will be made publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21226 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Frequency-Aware Gaussian Splatting Decomposition Lavi, Yishai Segre, Leo Avidan, Shai Computer Vision and Pattern Recognition 3D Gaussian Splatting (3D-GS) enables efficient novel view synthesis, but treats all frequencies uniformly, making it difficult to separate coarse structure from fine detail. Recent works have started to exploit frequency signals, but lack explicit frequency decomposition of the 3D representation itself. We propose a frequency-aware decomposition that organizes 3D Gaussians into groups corresponding to Laplacian-pyramid subbands of the input images. Each group is trained with spatial frequency regularization to confine it to its target frequency, while higher-frequency bands use signed residual colors to capture fine details that may be missed by lower-frequency reconstructions. A progressive coarse-to-fine training schedule stabilizes the decomposition. Our method achieves state-of-the-art reconstruction quality and rendering speed among all LOD-capable methods. In addition to improved interpretability, our method enables dynamic level-of-detail rendering, progressive streaming, foveated rendering, promptable 3D focus, and artistic filtering. Our code will be made publicly available. |
| title | Frequency-Aware Gaussian Splatting Decomposition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21226 |