# Learning Multi-Human Optical Flow

arXiv: https://arxiv.org/abs/1910.11667 · HTML: https://mlsanity.com/paper/1910.11667/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2019.

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

- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)
- [Tora: Trajectory-oriented Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2407.21705/) (2024)
- [LEAP: Learning Articulated Occupancy of People](https://mlsanity.com/paper/2104.06849/) (2021)
- [AutoFlow: Learning a Better Training Set for Optical Flow](https://mlsanity.com/paper/2104.14544/) (2021)
- [SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements](https://mlsanity.com/paper/2104.07660/) (2021)
- [UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture](https://mlsanity.com/paper/2208.01633/) (2022)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [3D Segmentation of Humans in Point Clouds with Synthetic Data](https://mlsanity.com/paper/2212.00786/) (2022)
- [BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image](https://mlsanity.com/paper/2105.09936/) (2021)
- [Multi-person Implicit Reconstruction from a Single Image](https://mlsanity.com/paper/2104.09283/) (2021)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements](https://mlsanity.com/paper/2306.07399/) (2023)
- [SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation](https://mlsanity.com/paper/2308.16876/) (2023)
- [LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow](https://mlsanity.com/paper/2409.05688/) (2024)
- [OmniFlow: Human Omnidirectional Optical Flow](https://mlsanity.com/paper/2104.07960/) (2021)
- [H-MoRe: Learning Human-centric Motion Representation for Action Analysis](https://mlsanity.com/paper/2504.10676/) (2025)
- [FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Model](https://mlsanity.com/paper/2409.05396/) (2024)
- [RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo](https://mlsanity.com/paper/2505.09368/) (2025)
- [PLT-D3: A High-fidelity Dynamic Driving Simulation Dataset for Stereo Depth and Scene Flow](https://mlsanity.com/paper/2406.07667/) (2024)
- [Render In-between: Motion Guided Video Synthesis for Action Interpolation](https://mlsanity.com/paper/2111.01029/) (2021)
- [Bootstrapping Human Optical Flow and Pose](https://mlsanity.com/paper/2210.15121/) (2022)
- [MESD: Exploring Optical Flow Assessment on Edge of Motion Objects with Motion Edge Structure Difference](https://mlsanity.com/paper/2104.05916/) (2021)
- [SHARE: Single-view Human Adversarial REconstruction](https://mlsanity.com/paper/2401.00343/) (2023)
- [Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes](https://mlsanity.com/paper/2402.02736/) (2024)

## Abstract (arXiv)

The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does not cover the domain of human motion. Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset. We use a 3D model of the human body and motion capture data to synthesize realistic flow fields in both single- and multi-person images. We then train optical flow networks to estimate human flow fields from pairs of images. We demonstrate that our trained networks are more accurate than a wide range of top methods on held-out test data and that they can generalize well to real image sequences. The code, trained models and the dataset are available for research.