# Unsupervised cycle-consistent deformation for shape matching

arXiv: https://arxiv.org/abs/1907.03165 · HTML: https://mlsanity.com/paper/1907.03165/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2019.

## Built on by (most cited first, 23 of 23)

- [Garment3DGen: 3D Garment Stylization and Texture Generation](https://mlsanity.com/paper/2403.18816/) (2024)
- [Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2109.06619/) (2021)
- [Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching](https://mlsanity.com/paper/2303.10971/) (2023)
- [Learning 3D Dense Correspondence via Canonical Point Autoencoder](https://mlsanity.com/paper/2107.04867/) (2021)
- [Reliable Inlier Evaluation for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2202.11292/) (2022)
- [A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching](https://mlsanity.com/paper/2204.12805/) (2022)
- [Implicit field supervision for robust non-rigid shape matching](https://mlsanity.com/paper/2203.07694/) (2022)
- [Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching](https://mlsanity.com/paper/2211.14604/) (2022)
- [Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases](https://mlsanity.com/paper/2104.06950/) (2021)
- [Representing Shape Collections with Alignment-Aware Linear Models](https://mlsanity.com/paper/2109.01605/) (2021)
- [Intuitive Shape Editing in Latent Space](https://mlsanity.com/paper/2111.12488/) (2021)
- [Synchronous Diffusion for Unsupervised Smooth Non-Rigid 3D Shape Matching](https://mlsanity.com/paper/2407.08244/) (2024)
- [Consistent Two-Flow Network for Tele-Registration of Point Clouds](https://mlsanity.com/paper/2106.00329/) (2021)
- [NeuralMLS: Geometry-Aware Control Point Deformation](https://mlsanity.com/paper/2201.01873/) (2022)
- [Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence](https://mlsanity.com/paper/2108.11609/) (2021)
- [Deformation-Guided Unsupervised Non-Rigid Shape Matching](https://mlsanity.com/paper/2311.15668/) (2023)
- [CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation](https://mlsanity.com/paper/2504.12800/) (2025)
- [Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects](https://mlsanity.com/paper/2212.14276/) (2022)
- [Overlap Bias Matching is Necessary for Point Cloud Registration](https://mlsanity.com/paper/2308.09364/) (2023)
- [CRAFT: Designing Creative and Functional 3D Objects](https://mlsanity.com/paper/2412.03889/) (2024)
- [NF3DM: Combining Neural Fields and Deformation Models for 3D Non-Rigid Motion Reconstruction](https://mlsanity.com/paper/2412.08511/) (2024)
- [Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases](https://mlsanity.com/paper/2111.06838/) (2021)
- [Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach](https://mlsanity.com/paper/2509.06862/) (2025)

## Abstract (arXiv)

We propose a self-supervised approach to deep surface deformation. Given a pair of shapes, our algorithm directly predicts a parametric transformation from one shape to the other respecting correspondences. Our insight is to use cycle-consistency to define a notion of good correspondences in groups of objects and use it as a supervisory signal to train our network. Our method does not rely on a template, assume near isometric deformations or rely on point-correspondence supervision. We demonstrate the efficacy of our approach by using it to transfer segmentation across shapes. We show, on Shapenet, that our approach is competitive with comparable state-of-the-art methods when annotated training data is readily available, but outperforms them by a large margin in the few-shot segmentation scenario.