Data

Tools

Indexes

Applications

Experiments

Open Source Science

awesome-point-cloud-completion

This repository catalogs the papers I referenced while completing a project on point cloud completion using diffusion.

https://github.com/hitcslj/awesome-point-cloud-completion

Science Score: 41.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org, ieee.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.1%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

This repository catalogs the papers I referenced while completing a project on point cloud completion using diffusion.

Basic Info
  • Host: GitHub
  • Owner: hitcslj
  • License: mit
  • Default Branch: main
  • Size: 13.6 MB
Statistics
  • Stars: 5
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License Citation

README.md

Awesome-Point-Cloud-Completion Awesome

This repository catalogs the papers I referenced while completing a project on point cloud completion using diffusion.

How to submit a pull request?

Table of Contents

Survey

Papers

Point-based - [PCN: Point Completion Network](https://arxiv.org/abs/1808.00671), Yuan et al., 3DV 2018 | [github](https://github.com/wentaoyuan/pcn) | [bibtext](./citations/pcn.txt) - [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://arxiv.org/abs/2108.08839), Yu et al., ICCV 2021 | [github](https://github.com/yuxumin/PoinTr) | [bibtext](./citations/pointr.txt) - [A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion](https://arxiv.org/abs/2112.03530), Lyu et al., ICLR 2022 | [github](https://github.com/ZhaoyangLyu/Point_Diffusion_Refinement) | [bibtext](./citations/PDR.txt) - [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://arxiv.org/abs/2301.04545), Yu et al., TPAMI 2023 | [github](https://github.com/yuxumin/PoinTr) | [bibtext](./citations/AdaPoinTr.txt) - [PointAttN: You Only Need Attention for Point Cloud Completion](https://ojs.aaai.org/index.php/AAAI/article/view/28356), Wang et al., AAAI 2024 | [github](https://github.com/ohhhyeahhh/PointAttN) | [bibtext](./citations/pointAttn.txt) - [T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy](https://arxiv.org/abs/2407.05008v1), Duan et al., ECCV 2024 | [github](https://github.com/df-boy/T-CorresNet) | [bibtext](./citations/corresnet.txt)
Voxel-based - [High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference](https://arxiv.org/abs/1709.07599), Han et al., ICCV 2017 | [bibtext](./citations/pcn.txt) - [Learning 3D Shape Completion under Weak Supervision](https://arxiv.org/abs/1805.07290), Stutz et al., CVPR 2018 | [github](https://github.com/davidstutz/cvpr2018-shape-completion) | [bibtext](./citations/scweak.txt) - [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://arxiv.org/abs/1904.07601), Liu et al., CVPR 2019 | [github](https://github.com/Yochengliu/Relation-Shape-CNN) | [bibtext](./citations/rscnn.txt)
PointVoxel(hybrid)-based - [Point-Voxel CNN for Efficient 3D Deep Learning](https://arxiv.org/abs/1907.03739), Liu et al., NeurIPS 2019 | [github](https://github.com/mit-han-lab/pvcnn) | [bibtext](./citations/pvcnn.txt) - [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://arxiv.org/abs/2006.03761), Xie et al., ECCV 2020 | [github](https://github.com/hzxie/GRNet) | [bibtext](./citations/grnet.txt) - [3D Shape Generation and Completion through Point-Voxel Diffusion](https://arxiv.org/abs/2104.03670), Zhou et al., ICCV 2021 | [github](https://github.com/alexzhou907/PVD) | [bibtext](./citations/pvd.txt)
TSDF-based - [Diffusion-SDF: Text-to-Shape via Voxelized Diffusion](https://arxiv.org/abs/2212.03293), Li et al., CVPR 2023 | [github](https://github.com/ttlmh/Diffusion-SDF) | [bibtext](./citations/diffusionsdf.txt) - [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://arxiv.org/abs/2306.16329), Chu et al., NeurIPS 2024 | [bibtext](./citations/diffcomplete.txt)
Latent feature-based - [LION: Latent Point Diffusion Models for 3D Shape Generation](https://arxiv.org/abs/2210.06978), Zeng et al., NeurIPS 2022 | [github](https://github.com/nv-tlabs/LION) | [bibtext](./citations/lion.txt)
Neural Repersentation-based - [Point-Cloud Completion with Pretrained Text-to-image Diffusion Models](https://arxiv.org/abs/2306.10533), Kasten et al., NeurIPS 2024| [github](https://github.com/NVlabs/sds-complete) | [bibtext](./citations/sds-complete.txt) - [Zero-shot Point Cloud Completion Via 2D Priors](https://arxiv.org/abs/2404.06814), Huang et al., arXiv 2024 | [bibtext](./citations/zeropc.txt)

Benchmarks and Datasets

Talks

Challenge

Implementations

  • TODO

License

awesome point cloud completion is released under the MIT license.

Contact

Primary contact: hitcslj@stu.hit.edu.cn. You can also contact: hitcszgq@stu.hit.edu.cn.

Owner

  • Name: Jian Liu
  • Login: hitcslj
  • Kind: user
  • Location: Harbin, Heilongjiang, China
  • Company: Harbin Institute of Technology

PhD Student @ HIT | Research Intern @ Megvii-reseach

Citation (citations/AdaPoinTr.txt) 

@inproceedings{yu2021pointr,
  title={Pointr: Diverse point cloud completion with geometry-aware transformers},
  author={Yu, Xumin and Rao, Yongming and Wang, Ziyi and Liu, Zuyan and Lu, Jiwen and Zhou, Jie},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  pages={12498--12507},
  year={2021}
}

GitHub Events

Total
  • Watch event: 10
  • Fork event: 1
Last Year
  • Watch event: 10
  • Fork event: 1