# Dense Human Body Correspondences Using Convolutional Networks

arXiv: https://arxiv.org/abs/1511.05904 · HTML: https://mlsanity.com/paper/1511.05904/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2015.

## Built on by (most cited first, 26 of 26)

- [Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera](https://mlsanity.com/paper/2106.08059/) (2021)
- [A Survey of Non-Rigid 3D Registration](https://mlsanity.com/paper/2203.07858/) (2022)
- [Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration](https://mlsanity.com/paper/2104.08160/) (2021)
- [Zero-Shot 3D Shape Correspondence](https://mlsanity.com/paper/2306.03253/) (2023)
- [Contact-Aware Retargeting of Skinned Motion](https://mlsanity.com/paper/2109.07431/) (2021)
- [VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds](https://mlsanity.com/paper/2110.08729/) (2021)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation](https://mlsanity.com/paper/2409.11682/) (2024)
- [GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models](https://mlsanity.com/paper/2304.10523/) (2023)
- [Beyond Complete Shapes: A Benchmark for Quantitative Evaluation of 3D Shape Surface Matching Algorithms](https://mlsanity.com/paper/2411.03511/) (2024)
- [Self-supervised 3D Human Mesh Recovery from Noisy Point Clouds](https://mlsanity.com/paper/2107.07539/) (2021)
- [LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling](https://mlsanity.com/paper/2208.08622/) (2022)
- [Deep Virtual Markers for Articulated 3D Shapes](https://mlsanity.com/paper/2108.09000/) (2021)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Persistent Homology Meets Object Unity: Object Recognition in Clutter](https://mlsanity.com/paper/2305.03815/) (2023)
- [BLiSS: Bootstrapped Linear Shape Space](https://mlsanity.com/paper/2309.01765/) (2023)
- [CLOI: An Automated Benchmark Framework For Generating Geometric Digital Twins Of Industrial Facilities](https://mlsanity.com/paper/2101.01355/) (2021)
- [Semi-supervised Dense Keypoints Using Unlabeled Multiview Images](https://mlsanity.com/paper/2109.09299/) (2021)
- [Learning Canonical Embedding for Non-rigid Shape Matching](https://mlsanity.com/paper/2110.02994/) (2021)
- [SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration](https://mlsanity.com/paper/2405.20188/) (2024)
- [Joint Symmetry Detection and Shape Matching for Non-Rigid Point Cloud](https://mlsanity.com/paper/2112.02713/) (2021)
- [Synthetic Point Cloud Generation for Class Segmentation Applications](https://mlsanity.com/paper/2205.03738/) (2022)
- [Revisiting Lesion Tracking in 3D Total Body Photography](https://mlsanity.com/paper/2412.07132/) (2024)
- [NFR: Neural Feature-Guided Non-Rigid Shape Registration](https://mlsanity.com/paper/2505.22445/) (2025)
- [LUIVITON: Learned Universal Interoperable VIrtual Try-ON](https://mlsanity.com/paper/2509.05030/) (2025)
- [Best Segmentation Buddies for Image-Shape Correspondence](https://mlsanity.com/paper/2605.18193/) (2026)

## Abstract (arXiv)

We propose a deep learning approach for finding dense correspondences between 3D scans of people. Our method requires only partial geometric information in the form of two depth maps or partial reconstructed surfaces, works for humans in arbitrary poses and wearing any clothing, does not require the two people to be scanned from similar viewpoints, and runs in real time. We use a deep convolutional neural network to train a feature descriptor on depth map pixels, but crucially, rather than training the network to solve the shape correspondence problem directly, we train it to solve a body region classification problem, modified to increase the smoothness of the learned descriptors near region boundaries. This approach ensures that nearby points on the human body are nearby in feature space, and vice versa, rendering the feature descriptor suitable for computing dense correspondences between the scans. We validate our method on real and synthetic data for both clothed and unclothed humans, and show that our correspondences are more robust than is possible with state-of-the-art unsupervised methods, and more accurate than those found using methods that require full watertight 3D geometry.