Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination


  • Peng-Shuai Wang Microsoft Research Asia
  • Yu-Qi Yang Tsinghua University Microsoft Research Asia
  • Qian-Fang Zou University of Science and Technology of China Microsoft Research Asia
  • Zhirong Wu Microsoft Research Asia
  • Yang Liu Microsoft Research Asia
  • Xin Tong Microsoft Research Asia


3D Computer Vision


We propose an unsupervised method for learning a generic and efficient shape encoding network for different shape analysis tasks. Our key idea is to jointly encode and learn shape and point features from unlabeled 3D point clouds. For this purpose, we adapt HRNet to octree-based convolutional neural networks for jointly encoding shape and point features with fused multiresolution subnetworks and design a simple-yet-efficient Multiresolution Instance Discrimination (MID) loss for jointly learning the shape and point features. Our network takes a 3D point cloud as input and output both shape and point features. After training, Our network is concatenated with simple task-specific back-ends and fine-tuned for different shape analysis tasks. We evaluate the efficacy and generality of our method with a set of shape analysis tasks, including shape classification, semantic shape segmentation, as well as shape registration tasks. With simple back-ends, our network demonstrates the best performance among all unsupervised methods and achieves competitive performance to supervised methods. For fine-grained shape segmentation on the PartNet dataset, our method even surpasses existing supervised methods by a large margin.




How to Cite

Wang, P.-S., Yang, Y.-Q., Zou, Q.-F., Wu, Z., Liu, Y., & Tong, X. (2021). Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 2773-2781. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16382



AAAI Technical Track on Computer Vision III