Investigating Domain Gaps for Indoor 3D Object Detection
By: Zijing Zhao , Zhu Xu , Qingchao Chen and more
Potential Business Impact:
Helps robots see objects in different rooms.
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/.
Similar Papers
Domain Adaptation for Different Sensor Configurations in 3D Object Detection
CV and Pattern Recognition
Helps self-driving cars see better with different sensors.
Real-Time 3D Object Detection with Inference-Aligned Learning
CV and Pattern Recognition
Helps robots see and understand objects in 3D.
Towards 3D Objectness Learning in an Open World
CV and Pattern Recognition
Finds any object in 3D, even new ones.