Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909189052301312 |
|---|---|
| author | Liu, Junchen Hu, Wenbo Yang, Zhuo Chen, Jianteng Wang, Guoliang Chen, Xiaoxue Cai, Yantong Gao, Huan-ang Zhao, Hao |
| author_facet | Liu, Junchen Hu, Wenbo Yang, Zhuo Chen, Jianteng Wang, Guoliang Chen, Xiaoxue Cai, Yantong Gao, Huan-ang Zhao, Hao |
| contents | Despite significant advancements in Neural Radiance Fields (NeRFs), the renderings may still suffer from aliasing and blurring artifacts, since it remains a fundamental challenge to effectively and efficiently characterize anisotropic areas induced by the cone-casting procedure. This paper introduces a Ripmap-Encoded Platonic Solid representation to precisely and efficiently featurize 3D anisotropic areas, achieving high-fidelity anti-aliasing renderings. Central to our approach are two key components: Platonic Solid Projection and Ripmap encoding. The Platonic Solid Projection factorizes the 3D space onto the unparalleled faces of a certain Platonic solid, such that the anisotropic 3D areas can be projected onto planes with distinguishable characterization. Meanwhile, each face of the Platonic solid is encoded by the Ripmap encoding, which is constructed by anisotropically pre-filtering a learnable feature grid, to enable featurzing the projected anisotropic areas both precisely and efficiently by the anisotropic area-sampling. Extensive experiments on both well-established synthetic datasets and a newly captured real-world dataset demonstrate that our Rip-NeRF attains state-of-the-art rendering quality, particularly excelling in the fine details of repetitive structures and textures, while maintaining relatively swift training times. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02386 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids Liu, Junchen Hu, Wenbo Yang, Zhuo Chen, Jianteng Wang, Guoliang Chen, Xiaoxue Cai, Yantong Gao, Huan-ang Zhao, Hao Computer Vision and Pattern Recognition Graphics Despite significant advancements in Neural Radiance Fields (NeRFs), the renderings may still suffer from aliasing and blurring artifacts, since it remains a fundamental challenge to effectively and efficiently characterize anisotropic areas induced by the cone-casting procedure. This paper introduces a Ripmap-Encoded Platonic Solid representation to precisely and efficiently featurize 3D anisotropic areas, achieving high-fidelity anti-aliasing renderings. Central to our approach are two key components: Platonic Solid Projection and Ripmap encoding. The Platonic Solid Projection factorizes the 3D space onto the unparalleled faces of a certain Platonic solid, such that the anisotropic 3D areas can be projected onto planes with distinguishable characterization. Meanwhile, each face of the Platonic solid is encoded by the Ripmap encoding, which is constructed by anisotropically pre-filtering a learnable feature grid, to enable featurzing the projected anisotropic areas both precisely and efficiently by the anisotropic area-sampling. Extensive experiments on both well-established synthetic datasets and a newly captured real-world dataset demonstrate that our Rip-NeRF attains state-of-the-art rendering quality, particularly excelling in the fine details of repetitive structures and textures, while maintaining relatively swift training times. |
| title | Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solids |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2405.02386 |