RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications
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_ | 1866913301244411904 |
|---|---|
| author | Liu, Xingyu Zhang, Chenyangguang Wang, Gu Zhang, Ruida Ji, Xiangyang |
| author_facet | Liu, Xingyu Zhang, Chenyangguang Wang, Gu Zhang, Ruida Ji, Xiangyang |
| contents | In robotic vision, a de-facto paradigm is to learn in simulated environments and then transfer to real-world applications, which poses an essential challenge in bridging the sim-to-real domain gap. While mainstream works tackle this problem in the RGB domain, we focus on depth data synthesis and develop a range-aware RGB-D data simulation pipeline (RaSim). In particular, high-fidelity depth data is generated by imitating the imaging principle of real-world sensors. A range-aware rendering strategy is further introduced to enrich data diversity. Extensive experiments show that models trained with RaSim can be directly applied to real-world scenarios without any finetuning and excel at downstream RGB-D perception tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03962 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications Liu, Xingyu Zhang, Chenyangguang Wang, Gu Zhang, Ruida Ji, Xiangyang Computer Vision and Pattern Recognition In robotic vision, a de-facto paradigm is to learn in simulated environments and then transfer to real-world applications, which poses an essential challenge in bridging the sim-to-real domain gap. While mainstream works tackle this problem in the RGB domain, we focus on depth data synthesis and develop a range-aware RGB-D data simulation pipeline (RaSim). In particular, high-fidelity depth data is generated by imitating the imaging principle of real-world sensors. A range-aware rendering strategy is further introduced to enrich data diversity. Extensive experiments show that models trained with RaSim can be directly applied to real-world scenarios without any finetuning and excel at downstream RGB-D perception tasks. |
| title | RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.03962 |