Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
Not on the map. Why?
Abstract (arXiv)
Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced distribution of available points. In this paper, we present a novel method for restoring large-scale point clouds with limited and imbalanced ground-truth. Using rough boundary annotations for a region of interest, we project the original point clouds into a multiple-center-of-projection (MCOP) image, where fragments are projected to images of 5 channels (RGB, depth, and rotation). Completion of the original point cloud is reduced to inpainting the missing pixels in the MCOP images. Due to lack of complete structures and an unbalanced distribution of existing parts, we develop a self-supervised scheme which learns to infill the MCOP image with points resembling existing "complete" patches. Special losses are applied to further enhance the regularity and consistency of completed MCOP images, which is mapped back to 3D to form final restoration. Extensive experiments demonstrate the superiority of our method in completing 600+ incomplete and unbalanced archaeological structures in Peru.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 45 references that are in the map. First posted on arXiv 6 Mar 2025.
Builds on
17 of 45 references.
References · 17
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
- 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
- 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
- 2021Projected GANs Converge Fastercited by 204
- 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
- 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 107
- 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
- 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
- 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
- 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
- 2023P2C: Self-Supervised Point Cloud Completion from Single Partial Cloudscited by 19
5 more
- 2022Learning a Structured Latent Space for Unsupervised Point Cloud Completioncited by 17
- 2021Self-Supervised Point Cloud Completion via Inpaintingcited by 16
- 20173D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversarial Networkcited by 12
- 2023ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completioncited by 9
- 2024Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learningcited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.