HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree
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_ | 1866911856808951808 |
|---|---|
| author | Liu, Shaofan Chen, Junbo Zhu, Jianke |
| author_facet | Liu, Shaofan Chen, Junbo Zhu, Jianke |
| contents | Incremental scene reconstruction is essential to the navigation in robotics. Most of the conventional methods typically make use of either TSDF (truncated signed distance functions) volume or neural networks to implicitly represent the surface. Due to the voxel representation or involving with time-consuming sampling, they have difficulty in balancing speed, memory storage, and surface quality. In this paper, we propose a novel hybrid voxel-octree approach to effectively fuse octree with voxel structures so that we can take advantage of both implicit surface and explicit triangular mesh representation. Such sparse structure preserves triangular faces in the leaf nodes and produces partial meshes sequentially for incremental reconstruction. This storage scheme allows us to naturally optimize the mesh in explicit 3D space to achieve higher surface quality. We iteratively deform the mesh towards the target and recovers vertex colors by optimizing a shading model. Experimental results on several datasets show that our proposed approach is capable of quickly and accurately reconstructing a scene with realistic colors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17974 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree Liu, Shaofan Chen, Junbo Zhu, Jianke Robotics Computer Vision and Pattern Recognition Incremental scene reconstruction is essential to the navigation in robotics. Most of the conventional methods typically make use of either TSDF (truncated signed distance functions) volume or neural networks to implicitly represent the surface. Due to the voxel representation or involving with time-consuming sampling, they have difficulty in balancing speed, memory storage, and surface quality. In this paper, we propose a novel hybrid voxel-octree approach to effectively fuse octree with voxel structures so that we can take advantage of both implicit surface and explicit triangular mesh representation. Such sparse structure preserves triangular faces in the leaf nodes and produces partial meshes sequentially for incremental reconstruction. This storage scheme allows us to naturally optimize the mesh in explicit 3D space to achieve higher surface quality. We iteratively deform the mesh towards the target and recovers vertex colors by optimizing a shading model. Experimental results on several datasets show that our proposed approach is capable of quickly and accurately reconstructing a scene with realistic colors. |
| title | HVOFusion: Incremental Mesh Reconstruction Using Hybrid Voxel Octree |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.17974 |