# REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

arXiv: https://arxiv.org/abs/2504.04956 · HTML: https://mlsanity.com/paper/2504.04956/

## Key facts

- Cited by 14 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 54 of its 65 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## 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 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [Project Aria: A New Tool for Egocentric Multi-Modal AI Research](https://mlsanity.com/paper/2308.13561/) (2023)
- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [Monocular Expressive Body Regression through Body-Driven Attention](https://mlsanity.com/paper/2008.09062/) (2020)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild](https://mlsanity.com/paper/2406.09905/) (2024)
- [AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing](https://mlsanity.com/paper/2207.13784/) (2022)
- [Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model](https://mlsanity.com/paper/2304.08577/) (2023)
- [DiffCollage: Parallel Generation of Large Content with Diffusion Models](https://mlsanity.com/paper/2303.17076/) (2023)
- [DiffPose: Toward More Reliable 3D Pose Estimation](https://mlsanity.com/paper/2211.16940/) (2022)
- [Ego-Body Pose Estimation via Ego-Head Pose Estimation](https://mlsanity.com/paper/2212.04636/) (2022)

## Built on by (most cited first, 14 of 14)

- [FlexSelect: Flexible Token Selection for Efficient Long Video Understanding](https://mlsanity.com/paper/2506.00993/) (2025)
- [Towards Cross-View Point Correspondence in Vision-Language Models](https://mlsanity.com/paper/2512.04686/) (2025)
- [MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics](https://mlsanity.com/paper/2510.01619/) (2025)
- [ECHO: Ego-Centric modeling of Human-Object interactions](https://mlsanity.com/paper/2508.21556/) (2025)
- [Egocentric Visibility-Aware Human Pose Estimation](https://mlsanity.com/paper/2602.23618/) (2026)
- [CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation](https://mlsanity.com/paper/2603.09418/) (2026)
- [LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusion](https://mlsanity.com/paper/2509.25739/) (2025)
- [Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation](https://mlsanity.com/paper/2510.00527/) (2025)
- [Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs](https://mlsanity.com/paper/2511.16264/) (2025)
- [OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction](https://mlsanity.com/paper/2512.19283/) (2025)
- [Human Motion Estimation with Everyday Wearables](https://mlsanity.com/paper/2512.21209/) (2025)
- [EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality](https://mlsanity.com/paper/2602.05590/) (2026)
- [AG-EgoPose: Spatially Anchored Residual Correction with Action Context for Monocular Egocentric 3D Pose Estimation](https://mlsanity.com/paper/2603.25175/) (2026)
- [EgoRelight: Egocentric Human Capture and Illumination Recovery for Relightable and Photoreal Avatar Rendering](https://mlsanity.com/paper/2605.28401/) (2026)

## Abstract (arXiv)

We present REWIND (Real-Time Egocentric Whole-Body Motion Diffusion), a one-step diffusion model for real-time, high-fidelity human motion estimation from egocentric image inputs. While an existing method for egocentric whole-body (i.e., body and hands) motion estimation is non-real-time and acausal due to diffusion-based iterative motion refinement to capture correlations between body and hand poses, REWIND operates in a fully causal and real-time manner. To enable real-time inference, we introduce (1) cascaded body-hand denoising diffusion, which effectively models the correlation between egocentric body and hand motions in a fast, feed-forward manner, and (2) diffusion distillation, which enables high-quality motion estimation with a single denoising step. Our denoising diffusion model is based on a modified Transformer architecture, designed to causally model output motions while enhancing generalizability to unseen motion lengths. Additionally, REWIND optionally supports identity-conditioned motion estimation when identity prior is available. To this end, we propose a novel identity conditioning method based on a small set of pose exemplars of the target identity, which further enhances motion estimation quality. Through extensive experiments, we demonstrate that REWIND significantly outperforms the existing baselines both with and without exemplar-based identity conditioning.