mlsanityData to 14 Oct 2026

Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

arXiv 2111.06838 ↗First posted 12 Nov 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible. We have devised an optimization strategy that makes our method robust to noise and global motions, without a priori correspondences or pre-alignment steps. As a result, our approach outperforms state-of-the-art ones on several challenging datasets. The code is available at https://github.com/bednarikjan/temporally_coherent_surface_reconstruction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 72 references that are in the map. First posted on arXiv 12 Nov 2021.

Builds on

27 of 72 references.

References · 27

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  6. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  7. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  8. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  9. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  10. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  11. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  12. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
15 more
  1. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  2. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  3. 2020LIMP: Learning Latent Shape Representations with Metric Preservation Priorscited by 55
  4. 2020KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotationscited by 51
  5. 2019Shape Reconstruction by Learning Differentiable Surface Representationscited by 37
  6. 2020Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignmentcited by 35
  7. 2020Isometric Multi-Shape Matchingcited by 33
  8. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  9. 2019Unsupervised cycle-consistent deformation for shape matchingcited by 23
  10. 2020Better Patch Stitching for Parametric Surface Reconstructioncited by 21
  11. 2018Isospectralization, or how to hear shape, style, and correspondencecited by 18
  12. 2017Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networkscited by 17
  13. 2020Intrinsic Point Cloud Interpolation via Dual Latent Space Navigationcited by 8
  14. 2020Weakly Supervised Deep Functional Map for Shape Matchingcited by 8
  15. 2021Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlasescited by 7

Built on by

Not cited yet.