Point2Seq: Detecting 3D Objects As Sequences

Yujing Xue, Jiageng Mao, Minzhe Niu, Hang Xu, Michael Bi Mi, Wei Zhang, Xiaogang Wang, Xinchao Wang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 8521-8530


We present a simple and effective framework, named Point2Seq, for 3D object detection from point clouds. In contrast to previous methods that normally predict attributes of 3D objects all at once, we expressively model the interdependencies between attributes of 3D objects, which in turn enables a better detection accuracy. Specifically, we view each 3D object as a sequence of words and reformulate the 3D object detection task as decoding words from 3D scenes in an auto-regressive manner. We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words. The predicted words eventually constitute a set of sequences that completely describe the 3D objects in the scene, and all the predicted sequences are then automatically assigned to the respective ground truths through similarity-based sequence matching. Our approach is conceptually intuitive and can be readily plugged upon most existing 3D-detection backbones without adding too much computational overhead; the sequential decoding paradigm we proposed, on the other hand, can better exploit information from complex 3D scenes with the aid of preceding predicted words. Without bells and whistles, our method significantly outperforms the previous anchor- and center-based 3D object detection frameworks, yielding the new state-of-the-art on the challenging ONCE dataset as well as the Waymo Open Dataset. Code will be made publicly available.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Xue_2022_CVPR, author = {Xue, Yujing and Mao, Jiageng and Niu, Minzhe and Xu, Hang and Mi, Michael Bi and Zhang, Wei and Wang, Xiaogang and Wang, Xinchao}, title = {Point2Seq: Detecting 3D Objects As Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {8521-8530} }