Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2306.09001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913522918621184 |
|---|---|
| author | Li, Yiming Li, Sihang Liu, Xinhao Gong, Moonjun Li, Kenan Chen, Nuo Wang, Zijun Li, Zhiheng Jiang, Tao Yu, Fisher Wang, Yue Zhao, Hang Yu, Zhiding Feng, Chen |
| author_facet | Li, Yiming Li, Sihang Liu, Xinhao Gong, Moonjun Li, Kenan Chen, Nuo Wang, Zijun Li, Zhiheng Jiang, Tao Yu, Fisher Wang, Yue Zhao, Hang Yu, Zhiding Feng, Chen |
| contents | Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details from RGB input. However, progress in SSC, particularly in large-scale street views, is hindered by the scarcity of high-quality datasets. To address this issue, we introduce SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets (e.g., KITTI-360, nuScenes, and Waymo). SSCBench follows an established setup and format in the community, facilitating the easy exploration of SSC methods in various street views. We benchmark models using monocular, trinocular, and point cloud input to assess the performance gap resulting from sensor coverage and modality. Moreover, we have unified semantic labels across diverse datasets to simplify cross-domain generalization testing. We commit to including more datasets and SSC models to drive further advancements in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_09001 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving Li, Yiming Li, Sihang Liu, Xinhao Gong, Moonjun Li, Kenan Chen, Nuo Wang, Zijun Li, Zhiheng Jiang, Tao Yu, Fisher Wang, Yue Zhao, Hang Yu, Zhiding Feng, Chen Computer Vision and Pattern Recognition Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details from RGB input. However, progress in SSC, particularly in large-scale street views, is hindered by the scarcity of high-quality datasets. To address this issue, we introduce SSCBench, a comprehensive benchmark that integrates scenes from widely used automotive datasets (e.g., KITTI-360, nuScenes, and Waymo). SSCBench follows an established setup and format in the community, facilitating the easy exploration of SSC methods in various street views. We benchmark models using monocular, trinocular, and point cloud input to assess the performance gap resulting from sensor coverage and modality. Moreover, we have unified semantic labels across diverse datasets to simplify cross-domain generalization testing. We commit to including more datasets and SSC models to drive further advancements in this field. |
| title | SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.09001 |