Scene Reconstruction as Mapping Priors for 3D Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918517631090688 |
|---|---|
| author | Fu, Yang Zou, Yuliang Xiang, Hao Huang, Xin Bai, Yijing Song, Chen Shi, Weijing Thattai, Govind Anguelov, Dragomir Tan, Mingxing Li, Yingwei |
| author_facet | Fu, Yang Zou, Yuliang Xiang, Hao Huang, Xin Bai, Yijing Song, Chen Shi, Weijing Thattai, Govind Anguelov, Dragomir Tan, Mingxing Li, Yingwei |
| contents | In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust structural priors of the static environment, helping resolve ambiguities and correct for sensor data sparsity or noise, especially for distant objects or under adverse weather conditions. However, conventional High-Definition (HD) maps are resource-intensive to obtain and maintain, which presents a challenge for efficient, large-scale deployment. In this paper, we propose a scalable solution to systematically leverage mapping to improve 3D detection by overcoming two primary challenges. First, we introduce a pipeline to automatically build dense mapping priors from aggregated sensor data, eliminating the need for human labeling. Second, we design a novel Mapping Priors Augmented 3D Detection (MPA3D) framework to effectively integrate mapping priors with different sensor modalities. Extensive experiments on the Waymo Open Dataset demonstrate that our approach achieves new state-of-the-art results, proving the effectiveness of scalable reconstructed scene priors for enhancing 3D detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22997 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scene Reconstruction as Mapping Priors for 3D Detection Fu, Yang Zou, Yuliang Xiang, Hao Huang, Xin Bai, Yijing Song, Chen Shi, Weijing Thattai, Govind Anguelov, Dragomir Tan, Mingxing Li, Yingwei Computer Vision and Pattern Recognition In autonomous driving, mapping is critical for motion planning but remains an under-utilized resource for perception tasks such as 3D object detection. Maps can provide robust structural priors of the static environment, helping resolve ambiguities and correct for sensor data sparsity or noise, especially for distant objects or under adverse weather conditions. However, conventional High-Definition (HD) maps are resource-intensive to obtain and maintain, which presents a challenge for efficient, large-scale deployment. In this paper, we propose a scalable solution to systematically leverage mapping to improve 3D detection by overcoming two primary challenges. First, we introduce a pipeline to automatically build dense mapping priors from aggregated sensor data, eliminating the need for human labeling. Second, we design a novel Mapping Priors Augmented 3D Detection (MPA3D) framework to effectively integrate mapping priors with different sensor modalities. Extensive experiments on the Waymo Open Dataset demonstrate that our approach achieves new state-of-the-art results, proving the effectiveness of scalable reconstructed scene priors for enhancing 3D detection. |
| title | Scene Reconstruction as Mapping Priors for 3D Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.22997 |