paper-with-me

홈 › Papers

Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsampling

2021-12-08 · CVPR 2022 1 · Wanquan Feng, Jin Li, Hongrui Cai, Xiaonan Luo, Juyong Zhang

In this paper, we propose Neural Points, a novel point cloud representation and apply it to the arbitrary-factored upsampling task. Different from traditional point cloud representation where each point only represents a position or a local plane in the 3D space, each point in Neural Points represents a local continuous geometric shape via neural fields. Therefore, Neural Points contain more shape information and thus have a stronger representation ability. Neural Points is trained with surface containing rich geometric details, such that the trained model has enough expression ability for various shapes. Specifically, we extract deep local features on the points and construct neural fields through the local isomorphism between the 2D parametric domain and the 3D local patch. In the final, local neural fields are integrated together to form the global surface. Experimental results show that Neural Points has powerful representation ability and demonstrate excellent robustness and generalization ability. With Neural Points, we can resample point cloud with arbitrary resolutions, and it outperforms the state-of-the-art point cloud upsampling methods. Code is available at https://github.com/WanquanF/NeuralPoints.

📄 PDF Abstract BibTeX arXiv:2112.04148

Code (1)

wanquanf/neuralpoints 공식 구현 pytorch

Tasks

point cloud upsampling

Similar Papers 제목 키워드 기반

ASUR3D: Arbitrary Scale Upsampling and Refinement of 3D Point Clouds using Local Occupancy Fields

2023-10-02 · IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) 2023 10 · Akash Kumbar, Tejas Anvekar, Ramesh Ashok Tabib, Uma Mudenagudi

In this paper, we introduce ASUR3D, a novel methodology for the arbitrary-scale upsampling of 3D point clouds employing Local Occupancy Representation. Our proposed implicit occupancy representation enables efficient poi…

3D Reconstruction3D Shape Generation3D Shape RepresentationPoint Cloud Super Resolution+1

iPUNet:Iterative Cross Field Guided Point Cloud Upsampling

2023-10-13 · Guangshun Wei, Hao Pan, Shaojie Zhuang, Yuanfeng Zhou 외

Point clouds acquired by 3D scanning devices are often sparse, noisy, and non-uniform, causing a loss of geometric features. To facilitate the usability of point clouds in downstream applications, given such input, we pr…

point cloud upsampling

Sample-Based Point Cloud Decoder Networks

2019-09-25 · Erich Merrill, Alan Fern

Point clouds are a flexible and ubiquitous way to represent 3D objects with arbitrary resolution and precision. Previous work has shown that adapting encoder networks to match the semantics of their input point clouds ca…

Decoder

Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

2024-03-08 · Hang Du, Xuejun Yan, Jingjing Wang, Di Xie 외

Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem…

point cloud upsampling

Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points

2025-10-14 · Jiayi Kong, Chen Zong, Junkai Deng, Xuhui Chen 외 arxiv

Unsigned Distance Fields (UDFs) provide a flexible representation for 3D shapes with arbitrary topology, including open and closed surfaces, orientable and non-orientable geometries, and non-manifold structures. While re…

Point Clouds