# Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

arXiv: https://arxiv.org/abs/2111.06838 · HTML: https://mlsanity.com/paper/2111.06838/

## 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 (most cited first, 27 of 27)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [3D-CODED : 3D Correspondences by Deep Deformation](https://mlsanity.com/paper/1806.05228/) (2018)
- [Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence](https://mlsanity.com/paper/2003.14286/) (2020)
- [Deep Geometric Prior for Surface Reconstruction](https://mlsanity.com/paper/1811.10943/) (2018)
- [Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks](https://mlsanity.com/paper/1909.00321/) (2019)
- [Learning elementary structures for 3D shape generation and matching](https://mlsanity.com/paper/1908.04725/) (2019)
- [Unsupervised Learning of Shape and Pose with Differentiable Point Clouds](https://mlsanity.com/paper/1810.09381/) (2018)
- [Unsupervised Deep Learning for Structured Shape Matching](https://mlsanity.com/paper/1812.03794/) (2018)
- [LIMP: Learning Latent Shape Representations with Metric Preservation Priors](https://mlsanity.com/paper/2003.12283/) (2020)
- [KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations](https://mlsanity.com/paper/2002.12687/) (2020)
- [Shape Reconstruction by Learning Differentiable Surface Representations](https://mlsanity.com/paper/1911.11227/) (2019)
- [Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment](https://mlsanity.com/paper/2011.14723/) (2020)
- [Isometric Multi-Shape Matching](https://mlsanity.com/paper/2012.02689/) (2020)
- [Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction](https://mlsanity.com/paper/2103.16341/) (2021)
- [Unsupervised cycle-consistent deformation for shape matching](https://mlsanity.com/paper/1907.03165/) (2019)
- [Better Patch Stitching for Parametric Surface Reconstruction](https://mlsanity.com/paper/2010.07021/) (2020)
- [Isospectralization, or how to hear shape, style, and correspondence](https://mlsanity.com/paper/1811.11465/) (2018)
- [Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks](https://mlsanity.com/paper/1706.04496/) (2017)
- [Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation](https://mlsanity.com/paper/2004.01661/) (2020)
- [Weakly Supervised Deep Functional Map for Shape Matching](https://mlsanity.com/paper/2009.13339/) (2020)
- [Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases](https://mlsanity.com/paper/2104.06950/) (2021)

## 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.