# Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting

arXiv: https://arxiv.org/abs/2607.15890 · HTML: https://mlsanity.com/paper/2607.15890/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 51 of its 89 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [Hand Keypoint Detection in Single Images using Multiview Bootstrapping](https://mlsanity.com/paper/1704.07809/) (2017)
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020)
- [Project Aria: A New Tool for Egocentric Multi-Modal AI Research](https://mlsanity.com/paper/2308.13561/) (2023)
- [What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2204.06252/) (2022)
- [RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete](https://mlsanity.com/paper/2502.21257/) (2025)
- [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1907.11346/) (2019)
- [Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos](https://mlsanity.com/paper/2204.01696/) (2022)
- [Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos](https://mlsanity.com/paper/2104.07905/) (2021)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data](https://mlsanity.com/paper/2602.16710/) (2026)
- [YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss](https://mlsanity.com/paper/2204.06806/) (2022)
- [LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities](https://mlsanity.com/paper/2007.15781/) (2020)
- [Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment](https://mlsanity.com/paper/2306.05526/) (2023)
- [Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation](https://mlsanity.com/paper/2508.13998/) (2025)
- [EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding](https://mlsanity.com/paper/2406.08877/) (2024)

## Abstract (arXiv)

Perceiving multimodal cues and forecasting fine-grained actions from an egocentric (Ego) perspective is vital for applications like robot manipulation. However, previous studies either rely mainly on under-informed visual inputs to predict coarse human motions or follow the VRM/VLA paradigm, which suffers from insufficient robot data and the gap between human and robot embodiments. We observe that 3D hand pose naturally serves as a unified representation to bridge human-robot actions. Hence, we investigate an under-explored Vision-Language guided Egocentric 3D Hand Pose Forecasting (VL-EHPF) task, which aims to predict future Ego 3D hand poses from visual observations, a language instruction, and pose states. To overcome the limited field-of-view and highly dynamic motions in the Ego view, we propose a framework dubbed Exo2EgoPose, which innovatively leverages holistic and stable exocentric (Exo) demonstrations as guidance to compensate for partial and dynamic Ego-view cues. Specifically, we introduce a Dual-level Exocentric Reconstruction Module (DERM), which incorporates the paired Exo videos as supervision to reconstruct their video-level and chunked frame-level representations, thereby modeling spatial contexts and temporal dynamics. Then, the Global-to-Local Modulation Module (GLMM) utilizes the reconstructed hierarchical Exo representations for progressive feature refinement via attention mechanisms and adaptive modulation, enabling comprehensive Exo guidance for accurate Ego hand pose forecasting. Extensive experiments on textitAssemblyHands, textitEgo-Exo4D, and our newly constructed textitEgoMe-pose benchmarks show the superiority of our method, which outperforms state-of-the-art methods by a large margin. Moreover, it demonstrates an effective human-to-robot transfer capability and yields improvements on the textitCALVIN dataset.