Unsupervised Point Cloud Pre-Training via Occlusion Completion
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
Code (1)
Tasks
3D Point Cloud Linear ClassificationDecoderFew-Shot 3D Point Cloud ClassificationPoint Cloud ClassificationPoint Cloud Pre-trainingPoint Cloud SegmentationSemantic SegmentationUnsupervised 3D Point Cloud Linear EvaluationSimilar Papers 제목 키워드 기반
Learning a Structured Latent Space for Unsupervised Point Cloud Completion
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 CompletionLeveraging Single-View Images for Unsupervised 3D Point Cloud Completion
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 CompletionOcclusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy
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 UnderstandingSelf-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism
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 CompletionPre-Training by Completing Point Clouds
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…