# HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences

arXiv: https://arxiv.org/abs/2103.15573 · HTML: https://mlsanity.com/paper/2103.15573/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 77 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 30 of 42)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Monocular Total Capture: Posing Face, Body, and Hands in the Wild](https://mlsanity.com/paper/1812.01598/) (2018)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model](https://mlsanity.com/paper/1803.08225/) (2018)
- [Towards Accurate Multi-person Pose Estimation in the Wild](https://mlsanity.com/paper/1701.01779/) (2017)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Learning Dense Correspondence via 3D-guided Cycle Consistency](https://mlsanity.com/paper/1604.05383/) (2016)
- [Dense Pose Transfer](https://mlsanity.com/paper/1809.01995/) (2018)
- [GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints](https://mlsanity.com/paper/1807.06294/) (2018)
- [Unsupervised Learning of Landmarks by Descriptor Vector Exchange](https://mlsanity.com/paper/1908.06427/) (2019)

## Built on by (most cited first, 12 of 12)

- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relighting](https://mlsanity.com/paper/2201.04873/) (2022)
- [Versatile Multi-Modal Pre-Training for Human-Centric Perception](https://mlsanity.com/paper/2203.13815/) (2022)
- [Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis](https://mlsanity.com/paper/2111.05916/) (2021)
- [Free-Viewpoint RGB-D Human Performance Capture and Rendering](https://mlsanity.com/paper/2112.13889/) (2021)
- [BodyMap: Learning Full-Body Dense Correspondence Map](https://mlsanity.com/paper/2205.09111/) (2022)
- [LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling](https://mlsanity.com/paper/2208.08622/) (2022)
- [Normal-guided Garment UV Prediction for Human Re-texturing](https://mlsanity.com/paper/2303.06504/) (2023)
- [Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences](https://mlsanity.com/paper/2310.18438/) (2023)
- [Pattern Guided UV Recovery for Realistic Video Garment Texturing](https://mlsanity.com/paper/2407.10137/) (2024)
- [SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes](https://mlsanity.com/paper/2408.02291/) (2024)
- [Human Pose-Constrained UV Map Estimation](https://mlsanity.com/paper/2501.08815/) (2025)

## Abstract (arXiv)

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle large motion or visually ambiguous body parts, e.g., left vs. right hand. In contrast, we propose a deep learning framework that maps each pixel to a feature space, where the feature distances reflect the geodesic distances among pixels as if they were projected onto the surface of a 3D human scan. To this end, we introduce novel loss functions to push features apart according to their geodesic distances on the surface. Without any semantic annotation, the proposed embeddings automatically learn to differentiate visually similar parts and align different subjects into an unified feature space. Extensive experiments show that the learned embeddings can produce accurate correspondences between images with remarkable generalization capabilities on both intra and inter subjects.