paper-with-me

Papers

Unsupervised Point Cloud Pre-Training via Occlusion Completion

2020-10-02 · ICCV 2021 10 · Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matthew J. Kusner

We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct the occluded points; 3. Use the encoder weights as initialisation for downstream point cloud tasks. We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks. Specifically, we show that our method outperforms previous pre-training methods in object classification, and both part-based and semantic segmentation tasks. We study the pre-trained features and find that they lead to wide downstream minima, have high transformation invariance, and have activations that are highly correlated with part labels. Code and data are available at: https://github.com/hansen7/OcCo

📄 PDF Abstract BibTeX arXiv:2010.01089

Code (1)

hansen7/OcCo 공식 구현 pytorch

Tasks

3D Point Cloud Linear ClassificationDecoderFew-Shot 3D Point Cloud ClassificationPoint Cloud ClassificationPoint Cloud Pre-trainingPoint Cloud SegmentationSemantic SegmentationUnsupervised 3D Point Cloud Linear Evaluation

Similar Papers 제목 키워드 기반

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

2022-03-29 · CVPR 2022 1 · Yingjie Cai, Kwan-Yee Lin, Chao Zhang, Qiang Wang 외

Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging problem since there is no paired partial-compl…

Point Cloud Completion

Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion

2022-12-01 · Lintai Wu, Qijian Zhang, Junhui Hou, Yong Xu

Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the complete shape of an object based on its par…

Point Cloud Completion

Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy

2025-02-15 · Mingyang Zhao, Gaofeng Meng, Dong-Ming Yan

Non-rigid alignment of point clouds is crucial for scene understanding, reconstruction, and various computer vision and robotics tasks. Recent advancements in implicit deformation networks for non-rigid registration have…

Point Cloud RegistrationScene Understanding

Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism

2022-03-20 · Yiming Ren, Peishan Cong, Xinge Zhu, Yuexin Ma

Real scans always miss partial geometries of objects due to the self-occlusions, external-occlusions, and limited sensor resolutions. Point cloud completion aims to refer the complete shapes for incomplete 3D scans of ob…

Point Cloud Completion

Pre-Training by Completing Point Clouds

2020-09-28 · Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby 외

There has recently been a flurry of exciting advances in deep learning models on point clouds. However, these advances have been hampered by the difficulty of creating labelled point cloud datasets: sparse point clouds o…