CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction
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_ | 1866916410582630400 |
|---|---|
| author | Ye, Zhangchen Jiang, Tao Xu, Chenfeng Li, Yiming Zhao, Hang |
| author_facet | Ye, Zhangchen Jiang, Tao Xu, Chenfeng Li, Yiming Zhao, Hang |
| contents | Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approach that leverages temporal fusion through the geometric correspondence of voxels over time to improve the accuracy of 3D occupancy predictions. By sampling points along the line of sight of each voxel and integrating the features of these points from historical frames, we construct a cost volume feature map that refines current volume features for improved prediction outcomes. Our method takes advantage of parallax cues from historical observations and employs a data-driven approach to learn the cost volume. We validate the effectiveness of CVT-Occ through rigorous experiments on the Occ3D-Waymo dataset, where it outperforms state-of-the-art methods in 3D occupancy prediction with minimal additional computational cost. The code is released at \url{https://github.com/Tsinghua-MARS-Lab/CVT-Occ}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13430 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction Ye, Zhangchen Jiang, Tao Xu, Chenfeng Li, Yiming Zhao, Hang Computer Vision and Pattern Recognition Artificial Intelligence Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approach that leverages temporal fusion through the geometric correspondence of voxels over time to improve the accuracy of 3D occupancy predictions. By sampling points along the line of sight of each voxel and integrating the features of these points from historical frames, we construct a cost volume feature map that refines current volume features for improved prediction outcomes. Our method takes advantage of parallax cues from historical observations and employs a data-driven approach to learn the cost volume. We validate the effectiveness of CVT-Occ through rigorous experiments on the Occ3D-Waymo dataset, where it outperforms state-of-the-art methods in 3D occupancy prediction with minimal additional computational cost. The code is released at \url{https://github.com/Tsinghua-MARS-Lab/CVT-Occ}. |
| title | CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.13430 |