# MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement

arXiv: https://arxiv.org/abs/2604.03299 · HTML: https://mlsanity.com/paper/2604.03299/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion](https://mlsanity.com/paper/2312.07531/) (2023)
- [Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video](https://mlsanity.com/paper/2011.08627/) (2020)
- [HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling](https://mlsanity.com/paper/2204.13686/) (2022)
- [Single-Stage Multi-Person Pose Machines](https://mlsanity.com/paper/1908.09220/) (2019)
- [RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1902.09868/) (2019)
- [EgoHumans: An Egocentric 3D Multi-Human Benchmark](https://mlsanity.com/paper/2305.16487/) (2023)
- [ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints](https://mlsanity.com/paper/2210.03895/) (2022)
- [ReFit: Recurrent Fitting Network for 3D Human Recovery](https://mlsanity.com/paper/2308.11184/) (2023)
- [Reconstructing Humans with a Biomechanically Accurate Skeleton](https://mlsanity.com/paper/2503.21751/) (2025)
- [Towards Viewpoint-Invariant Visual Recognition via Adversarial Training](https://mlsanity.com/paper/2307.10235/) (2023)
- [ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer's Disease](https://mlsanity.com/paper/2310.15301/) (2023)
- [Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module](https://mlsanity.com/paper/2303.04346/) (2023)
- [Learning camera viewpoint using CNN to improve 3D body pose estimation](https://mlsanity.com/paper/1609.05522/) (2016)
- [Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition](https://mlsanity.com/paper/2304.00858/) (2023)

## Built on by (most cited first, 1 of 1)

- [Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection](https://mlsanity.com/paper/2604.27617/) (2026)

## Abstract (arXiv)

3D human pose estimation is a key enabling technology for applications such as healthcare monitoring, human-robot collaboration, and immersive gaming, but real-world deployment remains challenged by viewpoint variations. Existing methods struggle to generalize to unseen camera viewpoints, require large amounts of training data, and suffer from high inference latency. We propose MoViD, a viewpoint-invariant 3D human pose estimation framework that disentangles viewpoint information from motion features. The key idea is to extract viewpoint information from intermediate pose features and leverage it to enhance both the robustness and efficiency of pose estimation. MoViD introduces a view estimator that models key joint relationships to predict viewpoint information, and an orthogonal projection module to disentangle motion and view features, further enhanced through physics-grounded contrastive alignment across views. For real-time edge deployment, MoViD employs a frame-by-frame inference pipeline with a view-aware strategy that adaptively activates flip refinement based on the estimated viewpoint. Evaluations on nine public datasets and newly collected multiview UAV and gait analysis datasets show that MoViD reduces pose estimation error by over 24.2% compared to state-of-the-art methods, maintains robust performance under severe occlusions with 60% less training data, and achieves real-time inference at 15 FPS on NVIDIA edge devices.