Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.17439 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914015010095104 |
|---|---|
| author | Zhao, Zijing Xu, Zhu Chen, Qingchao Peng, Yuxin Liu, Yang |
| author_facet | Zhao, Zijing Xu, Zhu Chen, Qingchao Peng, Yuxin Liu, Yang |
| contents | As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited datasets, where the training and testing sets share the same distribution. In this paper, we consider the task of adapting indoor 3D object detectors from one dataset to another, presenting a comprehensive benchmark with ScanNet, SUN RGB-D and 3D Front datasets, as well as our newly proposed large-scale datasets ProcTHOR-OD and ProcFront generated by a 3D simulator. Since indoor point cloud datasets are collected and constructed in different ways, the object detectors are likely to overfit to specific factors within each dataset, such as point cloud quality, bounding box layout and instance features. We conduct experiments across datasets on different adaptation scenarios including synthetic-to-real adaptation, point cloud quality adaptation, layout adaptation and instance feature adaptation, analyzing the impact of different domain gaps on 3D object detectors. We also introduce several approaches to improve adaptation performances, providing baselines for domain adaptive indoor 3D object detection, hoping that future works may propose detectors with stronger generalization ability across domains. Our project homepage can be found in https://jeremyzhao1998.github.io/DAVoteNet-release/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17439 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Investigating Domain Gaps for Indoor 3D Object Detection Zhao, Zijing Xu, Zhu Chen, Qingchao Peng, Yuxin Liu, Yang Computer Vision and Pattern Recognition As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited datasets, where the training and testing sets share the same distribution. In this paper, we consider the task of adapting indoor 3D object detectors from one dataset to another, presenting a comprehensive benchmark with ScanNet, SUN RGB-D and 3D Front datasets, as well as our newly proposed large-scale datasets ProcTHOR-OD and ProcFront generated by a 3D simulator. Since indoor point cloud datasets are collected and constructed in different ways, the object detectors are likely to overfit to specific factors within each dataset, such as point cloud quality, bounding box layout and instance features. We conduct experiments across datasets on different adaptation scenarios including synthetic-to-real adaptation, point cloud quality adaptation, layout adaptation and instance feature adaptation, analyzing the impact of different domain gaps on 3D object detectors. We also introduce several approaches to improve adaptation performances, providing baselines for domain adaptive indoor 3D object detection, hoping that future works may propose detectors with stronger generalization ability across domains. Our project homepage can be found in https://jeremyzhao1998.github.io/DAVoteNet-release/. |
| title | Investigating Domain Gaps for Indoor 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.17439 |