Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909043071647744 |
|---|---|
| author | Ning, Kanglin Zhao, Yiran Li, Wenrui Sun, Shaoru Wang, Xingtao Fan, Xiaopeng |
| author_facet | Ning, Kanglin Zhao, Yiran Li, Wenrui Sun, Shaoru Wang, Xingtao Fan, Xiaopeng |
| contents | Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D features onto discrete 3D grids, which break geometric continuity and limit representation efficiency. To overcome this limitation, this paper proposes PanoGSDet, a monocular panoramic 3D detection framework built upon continuous semantic 3D Gaussian representations. The proposed framework comprises a panoramic depth estimation component and a semantic Gaussian component. The panoramic depth estimation component extracts the equirectangular semantic and depth features from the monocular panorama input. The semantic Gaussian component includes a semantic Gaussian lifting module that projects spherical features into 3D semantic Gaussians, a semantic Gaussian optimization module that refines these semantic Gaussians, and a Gaussian guided prediction head that generates 3D bounding boxes from optimized Gaussian representations. Extensive experiments on the Structured3D dataset demonstrate that our method significantly outperforms existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14601 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach Ning, Kanglin Zhao, Yiran Li, Wenrui Sun, Shaoru Wang, Xingtao Fan, Xiaopeng Computer Vision and Pattern Recognition Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D features onto discrete 3D grids, which break geometric continuity and limit representation efficiency. To overcome this limitation, this paper proposes PanoGSDet, a monocular panoramic 3D detection framework built upon continuous semantic 3D Gaussian representations. The proposed framework comprises a panoramic depth estimation component and a semantic Gaussian component. The panoramic depth estimation component extracts the equirectangular semantic and depth features from the monocular panorama input. The semantic Gaussian component includes a semantic Gaussian lifting module that projects spherical features into 3D semantic Gaussians, a semantic Gaussian optimization module that refines these semantic Gaussians, and a Gaussian guided prediction head that generates 3D bounding boxes from optimized Gaussian representations. Extensive experiments on the Structured3D dataset demonstrate that our method significantly outperforms existing methods. |
| title | Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14601 |