paper-with-me

Papers

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 objects. Current deep learning-based approaches rely on large-scale complete shapes in the training process, which are usually obtained from synthetic datasets. It is not applicable for real-world scans due to the domain gap. In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data. Based on the symmetry and similarity of vehicles, we make use of consecutive point cloud frames to construct vehicle memory bank as reference. We design a bottom-up mechanism to focus on both local geometry details and global shape features of inputs. In addition, we design a scene-graph in the network to pay attention to the missing parts by the aid of neighboring vehicles. Experiments show that TraPCC achieve good performance for real-scan completion on KITTI and nuScenes traffic datasets even without any complete data in training. We also show a downstream application of 3D detection, which benefits from our completion approach.

📄 PDF Abstract BibTeX arXiv:2203.10569

Code (0)

등록된 구현이 없습니다.

Tasks

Point Cloud Completion

Similar Papers 제목 키워드 기반

Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud

2025-09-26 · Jingjing Lu, Huilong Pi, Yunchuan Qin, Zhuo Tang 외 arxiv

Point cloud completion aims to reconstruct complete shapes from partial observations. Although current methods have achieved remarkable performance, they still have some limitations: Supervised methods heavily rely on gr…

Point Cloud CompletionPoint Clouds

ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion

2023-03-02 · CVPR 2023 1 · Sangmin Hong, Mohsen Yavartanoo, Reyhaneh Neshatavar, Kyoung Mu Lee

Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods o…

Point Cloud CompletionSelf-Supervised Learning

Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion

2022-04-20 · Zhaoxin Fan, Yulin He, Zhicheng Wang, Kejian Wu 외

Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, …

Point Cloud Completion

RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models

2024-09-16 · Başak Melis Öcal, Maxim Tatarchenko, Sezer Karaoglu, Theo Gevers

Point cloud completion aims to recover the complete 3D shape of an object from partial observations. While approaches relying on synthetic shape priors achieved promising results in this domain, their applicability and g…

ObjectPoint Cloud Completion

Cascaded Refinement Network for Point Cloud Completion with Self-supervision

2020-10-17 · Xiaogang Wang, Marcelo H Ang Jr, Gim Hee Lee

Point clouds are often sparse and incomplete, which imposes difficulties for real-world applications. Existing shape completion methods tend to generate rough shapes without fine-grained details. Considering this, we int…

3D Object ClassificationPoint Cloud Completion