Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds

by   Jiacheng Wei, et al.

Semantic segmentation on 3D point clouds is an important task for 3D scene understanding. While dense labeling on 3D data is expensive and time-consuming, only a few works address weakly supervised semantic point cloud segmentation methods to relieve the labeling cost by learning from simpler and cheaper labels. Meanwhile, there are still huge performance gaps between existing weakly supervised methods and state-of-the-art fully supervised methods. In this paper, we train a semantic point cloud segmentation network with only a small portion of points being labeled. We argue that we can better utilize the limited supervision information as we densely propagate the supervision signal from the labeled points to other points within and across the input samples. Specifically, we propose a cross-sample feature reallocating module to transfer similar features and therefore re-route the gradients across two samples with common classes and an intra-sample feature redistribution module to propagate supervision signals on unlabeled points across and within point cloud samples. We conduct extensive experiments on public datasets S3DIS and ScanNet. Our weakly supervised method with only 10% and 1% of labels can produce compatible results with the fully supervised counterpart.


page 1

page 3

page 4

page 7


Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds

Point clouds provide intrinsic geometric information and surface context...

CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation

We study the task of weakly-supervised point cloud semantic segmentation...

A new weakly supervised approach for ALS point cloud semantic segmentation

While there are novel point cloud semantic segmentation schemes that con...

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Weakly supervised point cloud segmentation, i.e. semantically segmenting...

Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels

Point cloud analysis has received much attention recently; and segmentat...

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation

Since the preparation of labeled data for training semantic segmentation...

3D Spatial Recognition without Spatially Labeled 3D

We introduce WyPR, a Weakly-supervised framework for Point cloud Recogni...

Please sign up or login with your details

Forgot password? Click here to reset