Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.06505 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913581616857088 |
|---|---|
| author | Zhang, Chenhao Zhou, Yongyang Zhang, Lei |
| author_facet | Zhang, Chenhao Zhou, Yongyang Zhang, Lei |
| contents | The neural radiance fields (NeRF) have emerged as a prominent methodology for synthesizing realistic images of novel views. While neural radiance representations based on voxels or mesh individually offer distinct advantages, excelling in either rendering quality or speed, each has limitations in the other aspect. In response, we propose a hybrid representation named Vosh, seamlessly combining both voxel and mesh components in hybrid rendering for view synthesis. Vosh is meticulously crafted by optimizing the voxel grid based on neural rendering, strategically meshing a portion of the volumetric density field to surface. Therefore, it excels in fast rendering scenes with simple geometry and textures through its mesh component, while simultaneously enabling high-quality rendering in intricate regions by leveraging voxel component. The flexibility of Vosh is showcased through the ability to adjust hybrid ratios, providing users the ability to control the balance between rendering quality and speed based on flexible usage. Experimental results demonstrate that our method achieves commendable trade-off between rendering quality and speed, and notably has real-time performance on mobile devices. The interactive web demo and code are available at https://zyyzyy06.github.io/Vosh. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06505 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Voxel-Mesh Hybrid Representation for Real-Time View Synthesis Zhang, Chenhao Zhou, Yongyang Zhang, Lei Computer Vision and Pattern Recognition The neural radiance fields (NeRF) have emerged as a prominent methodology for synthesizing realistic images of novel views. While neural radiance representations based on voxels or mesh individually offer distinct advantages, excelling in either rendering quality or speed, each has limitations in the other aspect. In response, we propose a hybrid representation named Vosh, seamlessly combining both voxel and mesh components in hybrid rendering for view synthesis. Vosh is meticulously crafted by optimizing the voxel grid based on neural rendering, strategically meshing a portion of the volumetric density field to surface. Therefore, it excels in fast rendering scenes with simple geometry and textures through its mesh component, while simultaneously enabling high-quality rendering in intricate regions by leveraging voxel component. The flexibility of Vosh is showcased through the ability to adjust hybrid ratios, providing users the ability to control the balance between rendering quality and speed based on flexible usage. Experimental results demonstrate that our method achieves commendable trade-off between rendering quality and speed, and notably has real-time performance on mobile devices. The interactive web demo and code are available at https://zyyzyy06.github.io/Vosh. |
| title | Voxel-Mesh Hybrid Representation for Real-Time View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.06505 |