# ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery

arXiv: https://arxiv.org/abs/2608.20308 · HTML: https://mlsanity.com/paper/2608.20308/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 39 of its 43 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 39)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [Learning to Estimate 3D Hand Pose from Single RGB Images](https://mlsanity.com/paper/1705.01389/) (2017)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World](https://mlsanity.com/paper/2309.17024/) (2023)
- [Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video](https://mlsanity.com/paper/2011.08627/) (2020)
- [Decoupling Human and Camera Motion from Videos in the Wild](https://mlsanity.com/paper/2302.12827/) (2023)
- [Cameras as Rays: Pose Estimation via Ray Diffusion](https://mlsanity.com/paper/2402.14817/) (2024)
- [HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos](https://mlsanity.com/paper/2411.19167/) (2024)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion](https://mlsanity.com/paper/2403.19417/) (2024)
- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos](https://mlsanity.com/paper/2501.02973/) (2025)
- [Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera](https://mlsanity.com/paper/2412.12861/) (2024)
- [GENMO: A GENeralist Model for Human MOtion](https://mlsanity.com/paper/2505.01425/) (2025)
- [Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.14747/) (2023)
- [Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba](https://mlsanity.com/paper/2407.09646/) (2024)

## Built on by (most cited first, 2 of 2)

- [UniWAM: Unified World-Action Model](https://mlsanity.com/paper/2610.02054/) (2026)
- [RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning](https://mlsanity.com/paper/2610.09455/) (2026)

## Abstract (arXiv)

Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-of-sight gaps. Existing single-frame and windowed temporal regressors fail when a hand shortly leaves the frame, while recent video diffusion models (VDMs) rely on heavy, stochastic multi-step sampling as pixel-space renderers. We instead repurpose VDM into a deterministic geometry encoder. A single forward pass over the clean latent exposes scene content beyond current observations, including occluded and out-of-sight hands. We introduce ACE-Ego-Hand, an offline clip-level framework that extracts features via a Deterministic Clean-Latent Encoder and decodes them with a Bidirectional Spatiotemporal Decoder. ACE-Ego-Hand recovers continuous bimanual trajectories with metric placement and no external detector, while a Ray-Based Camera Solver supports a second configuration that requires no test-time camera intrinsics. Across five egocentric benchmarks, ACE-Ego-Hand sets a new state of the art, cutting MPJPE-p by 30% on occlusion-heavy ARCTIC and 40% on HOT3D. These gains reach 46%-61% once out-of-sight hands are included in the evaluation, offering a scalable path from everyday human video to robot manipulation data.