DETR-based methods, which use multi-layer transformer decoders to refine object queries iteratively, have shown promising performance in 3D indoor object detection. However, the scene point features ...
It is a mix of MIT and the official DINOv3 License. All the codebase in this repository are completely open and can be used for research, education, and commercial purposes freely. The models trained ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results