3D Spatial Recognition without Spatially Labeled 3D

05/13/2021
by   Zhongzheng Ren, et al.
0

We introduce WyPR, a Weakly-supervised framework for Point cloud Recognition, requiring only scene-level class tags as supervision. WyPR jointly addresses three core 3D recognition tasks: point-level semantic segmentation, 3D proposal generation, and 3D object detection, coupling their predictions through self and cross-task consistency losses. We show that in conjunction with standard multiple-instance learning objectives, WyPR can detect and segment objects in point cloud data without access to any spatial labels at training time. We demonstrate its efficacy using the ScanNet and S3DIS datasets, outperforming prior state of the art on weakly-supervised segmentation by more than 6 In addition, we set up the first benchmark for weakly-supervised 3D object detection on both datasets, where WyPR outperforms standard approaches and establishes strong baselines for future work.

READ FULL TEXT

page 1

page 8

page 16

page 17

research
07/23/2021

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

Semantic segmentation on 3D point clouds is an important task for 3D sce...
research
04/08/2020

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

Point cloud analysis has received much attention recently; and segmentat...
research
12/18/2020

SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation

Most existing point cloud instance and semantic segmentation methods hea...
research
03/09/2019

Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

Indoor scenes exhibit rich hierarchical structure in 3D object layouts. ...
research
06/04/2021

ZeroWaste Dataset: Towards Automated Waste Recycling

Less than 35 leads to increased soil and sea pollution and is one of the...
research
12/20/2022

Weakly supervised training of universal visual concepts for multi-domain semantic segmentation

Deep supervised models have an unprecedented capacity to absorb large qu...
research
10/05/2018

Weakly Supervised Object Detection in Artworks

We propose a method for the weakly supervised detection of objects in pa...

Please sign up or login with your details

Forgot password? Click here to reset