mlsanityData to 7 Oct 2026

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

arXiv 2104.06950 ↗First posted 14 Apr 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstructed surface as an atlas, using a neural network. Using canonical correspondences defined via the atlas, we encourage the reconstruction to be as isometric as possible across frames, leading to semantically-meaningful reconstruction. Through experiments and comparisons, we empirically show that our method achieves results that exceed that state of the art in the accuracy of unsupervised correspondences and accuracy of surface reconstruction.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 23 of its 55 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

23 of 55 references.

References · 23

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  6. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  9. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  10. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  11. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  12. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
11 more
  1. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  2. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  3. 2018Unsupervised Learning of Shape and Pose with Differentiable Point Cloudscited by 89
  4. 2018Unsupervised Deep Learning for Structured Shape Matchingcited by 81
  5. 2020LIMP: Learning Latent Shape Representations with Metric Preservation Priorscited by 54
  6. 2020KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotationscited by 50
  7. 2019Shape Reconstruction by Learning Differentiable Surface Representationscited by 37
  8. 2019Unsupervised cycle-consistent deformation for shape matchingcited by 23
  9. 2020Better Patch Stitching for Parametric Surface Reconstructioncited by 21
  10. 2017Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networkscited by 17
  11. 2020Intrinsic Point Cloud Interpolation via Dual Latent Space Navigationcited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 1.

7 papers.

  1. 2022CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphismcited by 56
  2. 2022φ-SfT: Shape-from-Template with a Physics-Based Deformation Modelcited by 23
  3. 2023GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Modelscited by 11
  4. 2023GAPS: Geometry-Aware, Physics-Based, Self-Supervised Neural Garment Drapingcited by 9
  5. 2024CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation from Arbitrary-Length Sequencescited by 6
  6. 2022Learning Joint Surface Atlasescited by 2
  7. 2021Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlasescited by 0