You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding
This addresses the tedious annotation problem in 3D scene understanding for researchers and practitioners, offering a weakly supervised solution that significantly reduces labeling costs while maintaining performance.
The paper tackles the problem of reducing annotation effort for 3D scene understanding by proposing a method that requires only one point label per object, using a self-training approach with iterative label propagation and relation networks to achieve results comparable to fully supervised methods on ScanNet-v2 and S3DIS datasets.
3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose ``One Thing One Click,'' meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate the per-category prototype to enhance the pseudo label quality and guide the iterative training. Besides, our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic and instance segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts. Codes and models are available at https://github.com/liuzhengzhe/One-Thing-One-Click.