Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining

11/30/2021
by   Yongbin Liao, et al.
3

Point cloud instance segmentation has achieved huge progress with the emergence of deep learning. However, these methods are usually data-hungry with expensive and time-consuming dense point cloud annotations. To alleviate the annotation cost, unlabeled or weakly labeled data is still less explored in the task. In this paper, we introduce the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision. To be specific, our SPIB architecture involves a two-stage learning procedure. For stage one, a bounding box proposal generation network is trained under a semi-supervised setting with perturbation consistency regularization (SPCR). The regularization works by enforcing an invariance of the bounding box predictions over different perturbations applied to the input point clouds, to provide self-supervision for network learning. For stage two, the bounding box proposals with SPCR are grouped into some subsets, and the instance masks are mined inside each subset with a novel semantic propagation module and a property consistency graph module. Moreover, we introduce a novel occupancy ratio guided refinement module to refine the instance masks. Extensive experiments on the challenging ScanNet v2 dataset demonstrate our method can achieve competitive performance compared with the recent fully-supervised methods.

READ FULL TEXT

page 2

page 4

page 6

page 9

page 12

research
06/02/2022

Semantic Instance Segmentation of 3D Scenes Through Weak Bounding Box Supervision

Current 3D segmentation methods heavily rely on large-scale point-cloud ...
research
02/22/2021

SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequences

Large labeled data sets are one of the essential basics of modern deep l...
research
12/01/2020

3D Guided Weakly Supervised Semantic Segmentation

Pixel-wise clean annotation is necessary for fully-supervised semantic s...
research
08/18/2022

Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization

Open-world instance segmentation (OWIS) aims to segment class-agnostic i...
research
01/09/2022

Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision

Learning dense point-wise semantics from unstructured 3D point clouds wi...
research
06/04/2019

Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds

We propose a novel, conceptually simple and general framework for instan...
research
10/13/2022

Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction

3D bounding boxes are a widespread intermediate representation in many c...

Please sign up or login with your details

Forgot password? Click here to reset