MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation
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_ | 1866916545370783744 |
|---|---|
| author | Seong, Minjae Kim, Jisong Bang, Geonho Jeong, Hawook Choi, Jun Won |
| author_facet | Seong, Minjae Kim, Jisong Bang, Geonho Jeong, Hawook Choi, Jun Won |
| contents | Accurate 3D perception is essential for understanding the environment in autonomous driving. Recent advancements in 3D semantic occupancy prediction have leveraged camera-LiDAR fusion to improve robustness and accuracy. However, current methods allocate computational resources uniformly across all voxels, leading to inefficiency, and they also fail to adequately address occlusions, resulting in reduced accuracy in challenging scenarios. We propose MR-Occ, a novel approach for camera-LiDAR fusion-based 3D semantic occupancy prediction, addressing these challenges through three key components: Hierarchical Voxel Feature Refinement (HVFR), Multi-scale Occupancy Decoder (MOD), and Pixel to Voxel Fusion Network (PVF-Net). HVFR improves performance by enhancing features for critical voxels, reducing computational cost. MOD introduces an `occluded' class to better handle regions obscured from sensor view, improving accuracy. PVF-Net leverages densified LiDAR features to effectively fuse camera and LiDAR data through a deformable attention mechanism. Extensive experiments demonstrate that MR-Occ achieves state-of-the-art performance on the nuScenes-Occupancy dataset, surpassing previous approaches by +5.2% in IoU and +5.3% in mIoU while using fewer parameters and FLOPs. Moreover, MR-Occ demonstrates superior performance on the SemanticKITTI dataset, further validating its effectiveness and generalizability across diverse 3D semantic occupancy benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation Seong, Minjae Kim, Jisong Bang, Geonho Jeong, Hawook Choi, Jun Won Computer Vision and Pattern Recognition Accurate 3D perception is essential for understanding the environment in autonomous driving. Recent advancements in 3D semantic occupancy prediction have leveraged camera-LiDAR fusion to improve robustness and accuracy. However, current methods allocate computational resources uniformly across all voxels, leading to inefficiency, and they also fail to adequately address occlusions, resulting in reduced accuracy in challenging scenarios. We propose MR-Occ, a novel approach for camera-LiDAR fusion-based 3D semantic occupancy prediction, addressing these challenges through three key components: Hierarchical Voxel Feature Refinement (HVFR), Multi-scale Occupancy Decoder (MOD), and Pixel to Voxel Fusion Network (PVF-Net). HVFR improves performance by enhancing features for critical voxels, reducing computational cost. MOD introduces an `occluded' class to better handle regions obscured from sensor view, improving accuracy. PVF-Net leverages densified LiDAR features to effectively fuse camera and LiDAR data through a deformable attention mechanism. Extensive experiments demonstrate that MR-Occ achieves state-of-the-art performance on the nuScenes-Occupancy dataset, surpassing previous approaches by +5.2% in IoU and +5.3% in mIoU while using fewer parameters and FLOPs. Moreover, MR-Occ demonstrates superior performance on the SemanticKITTI dataset, further validating its effectiveness and generalizability across diverse 3D semantic occupancy benchmarks. |
| title | MR-Occ: Efficient Camera-LiDAR 3D Semantic Occupancy Prediction Using Hierarchical Multi-Resolution Voxel Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.20480 |