3D Spatial Recognition without Spatially Labeled 3D
Zhongzheng Ren,Ishan Misra,Alexander G. Schwing,Rohit Girdhar +3 more
- 13 May 2021
- pp 13204-13213
71
TL;DR: WyPR as mentioned in this paper is a weakly-supervised framework for point cloud point cloud recognition, requiring only scene-level class tags as supervision, which can detect and segment objects in point cloud data without access to any spatial labels at training time.
read more
Abstract: 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% mIoU. 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 more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Metaverse: Taxonomy, Components, Applications, and Open Challenges
01 Jan 2022
TL;DR: In this article , the authors divide the concepts and essential techniques necessary for realizing the Metaverse into three components (i.e., hardware, software, and contents) rather than marketing or hardware approach to conduct a comprehensive analysis.
A Metaverse: Taxonomy, Components, Applications, and Open Challenges
Sang-Min Park,Young-Gab Kim +1 more
TL;DR: This paper divides the concepts and essential techniques necessary for realizing the Metaverse into three components (i.e., hardware, software, and contents) and three approaches and describes essential methods based on three components and techniques to Metaverse’s representative Ready Player One, Roblox, and Facebook research in the domain of films, games, and studies.
583
Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation using Bounding Boxes
TL;DR: In this paper , a weakly-supervised 3D semantic instance segmentation method is proposed to leverage 3D bounding box labels, which are easier and faster to annotate.
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
TL;DR: In this article , the authors propose a weak supervision method to implicitly augment highly sparse supervision signals, which achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort.
HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization
01 Jun 2022
TL;DR: Hybrid Contrastive Regularization (HybridCR) as discussed by the authors leverages both point consistency and contrastive regularization with pseudo-labels in an end-to-end manner.
56
References
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
R. Qi Charles,Hao Su,Mo Kaichun,Leonidas J. Guibas +3 more
- 21 Jul 2017
TL;DR: This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
Vision meets robotics: The KITTI dataset
TL;DR: A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system.
Learning Deep Features for Discriminative Localization
Bolei Zhou,Aditya Khosla,Agata Lapedriza,Aude Oliva,Antonio Torralba +4 more
- 27 Jun 2016
TL;DR: This work revisits the global average pooling layer proposed in [13], and sheds light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained on imagelevel labels.
Multitask Learning
Rich Caruana
- 01 Jul 1997
TL;DR: Multi-task Learning (MTL) as mentioned in this paper is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias.
•Posted Content
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TL;DR: A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly.