# Optical Flow-based 3D Human Motion Estimation from Monocular Video

arXiv: https://arxiv.org/abs/1703.00177 · HTML: https://mlsanity.com/paper/1703.00177/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2017.

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

- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild](https://mlsanity.com/paper/2103.10978/) (2021)
- [CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions](https://mlsanity.com/paper/2303.17948/) (2023)
- [Learning monocular 3D reconstruction of articulated categories from motion](https://mlsanity.com/paper/2103.16352/) (2021)
- [RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method](https://mlsanity.com/paper/2403.19501/) (2024)
- [STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion](https://mlsanity.com/paper/2401.01730/) (2024)
- [KBody: Towards general, robust, and aligned monocular whole-body estimation](https://mlsanity.com/paper/2304.11542/) (2023)
- [Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model](https://mlsanity.com/paper/2111.15404/) (2021)
- [ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate](https://mlsanity.com/paper/2503.21268/) (2025)
- [A Joint Visual Compression and Perception Framework for Neuralmorphic Spiking Camera](https://mlsanity.com/paper/2503.02725/) (2025)
- [Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture](https://mlsanity.com/paper/2604.00857/) (2026)
- [Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration](https://mlsanity.com/paper/2608.02285/) (2026)

## Abstract (arXiv)

We present a generative method to estimate 3D human motion and body shape from monocular video. Under the assumption that starting from an initial pose optical flow constrains subsequent human motion, we exploit flow to find temporally coherent human poses of a motion sequence. We estimate human motion by minimizing the difference between computed flow fields and the output of an artificial flow renderer. A single initialization step is required to estimate motion over multiple frames. Several regularization functions enhance robustness over time. Our test scenarios demonstrate that optical flow effectively regularizes the under-constrained problem of human shape and motion estimation from monocular video.