Co-Fix3D: Enhancing 3D Object Detection with Collaborative Refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916481357316096 |
|---|---|
| author | Li, Wenxuan Zou, Qin Chen, Chi Du, Bo Chen, Long Zhou, Jian Yu, Hongkai |
| author_facet | Li, Wenxuan Zou, Qin Chen, Chi Du, Bo Chen, Long Zhou, Jian Yu, Hongkai |
| contents | 3D object detection in driving scenarios faces the challenge of complex road environments, which can lead to the loss or incompleteness of key features, thereby affecting perception performance. To address this issue, we propose an advanced detection framework called Co-Fix3D. Co-Fix3D integrates Local and Global Enhancement (LGE) modules to refine Bird's Eye View (BEV) features. The LGE module uses Discrete Wavelet Transform (DWT) for pixel-level local optimization and incorporates an attention mechanism for global optimization. To handle varying detection difficulties, we adopt multi-head LGE modules, enabling each module to focus on targets with different levels of detection complexity, thus further enhancing overall perception capability. Experimental results show that on the nuScenes dataset's LiDAR benchmark, Co-Fix3D achieves 69.4\% mAP and 73.5\% NDS, while on the multimodal benchmark, it achieves 72.3\% mAP and 74.7\% NDS. The source code is publicly available at \href{https://github.com/rubbish001/Co-Fix3d}{https://github.com/rubbish001/Co-Fix3d}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07999 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Co-Fix3D: Enhancing 3D Object Detection with Collaborative Refinement Li, Wenxuan Zou, Qin Chen, Chi Du, Bo Chen, Long Zhou, Jian Yu, Hongkai Computer Vision and Pattern Recognition 3D object detection in driving scenarios faces the challenge of complex road environments, which can lead to the loss or incompleteness of key features, thereby affecting perception performance. To address this issue, we propose an advanced detection framework called Co-Fix3D. Co-Fix3D integrates Local and Global Enhancement (LGE) modules to refine Bird's Eye View (BEV) features. The LGE module uses Discrete Wavelet Transform (DWT) for pixel-level local optimization and incorporates an attention mechanism for global optimization. To handle varying detection difficulties, we adopt multi-head LGE modules, enabling each module to focus on targets with different levels of detection complexity, thus further enhancing overall perception capability. Experimental results show that on the nuScenes dataset's LiDAR benchmark, Co-Fix3D achieves 69.4\% mAP and 73.5\% NDS, while on the multimodal benchmark, it achieves 72.3\% mAP and 74.7\% NDS. The source code is publicly available at \href{https://github.com/rubbish001/Co-Fix3d}{https://github.com/rubbish001/Co-Fix3d}. |
| title | Co-Fix3D: Enhancing 3D Object Detection with Collaborative Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.07999 |