# Seeing the World and the Self from Egocentric Video

arXiv: https://arxiv.org/abs/2609.01276 · HTML: https://mlsanity.com/paper/2609.01276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [TTT3R: 3D Reconstruction as Test-Time Training](https://mlsanity.com/paper/2509.26645/) (2025)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild](https://mlsanity.com/paper/2406.09905/) (2024)
- [Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos](https://mlsanity.com/paper/2104.07905/) (2021)
- [Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2407.07532/) (2024)
- [Estimating Body and Hand Motion in an Ego-sensed World](https://mlsanity.com/paper/2410.03665/) (2024)
- [Human3R: Everyone Everywhere All at Once](https://mlsanity.com/paper/2510.06219/) (2025)
- [EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams](https://mlsanity.com/paper/2404.08640/) (2024)
- [Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input](https://mlsanity.com/paper/2504.08449/) (2025)
- [UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation](https://mlsanity.com/paper/2508.01126/) (2025)
- [4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time](https://mlsanity.com/paper/2506.18890/) (2025)
- [EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System](https://mlsanity.com/paper/2409.00343/) (2024)
- [EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatars](https://mlsanity.com/paper/2410.01835/) (2024)
- [Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos](https://mlsanity.com/paper/2411.09145/) (2024)

## Abstract (arXiv)

Complete 3D perception from egocentric video requires recovering the surrounding scene and the wearer's full-body motion in a shared metric frame. Existing methods typically address scene reconstruction and motion estimation separately: scene reconstruction methods ignore the wearer, whereas motion estimation methods lack explicit scene geometry and often depend on external trajectories. Joint recovery is challenging because the two tasks exhibit asymmetric visibility and require different prediction paradigms. The largely visible scene supports deterministic geometric regression, whereas the severely occluded body requires generative motion inference. We therefore propose RESELF (REconstructing the Scene and the sELF), a unified framework that couples deterministic metric geometry reconstruction with geometry-conditioned motion generation. RESELF adapts a geometry foundation model pre-trained on large-scale exocentric data to egocentric video using frame-wise scale and relative-pose consistency objectives. The resulting camera trajectory and latent geometric features condition a diffusion model that recovers the wearer's motion. A subsequent closed-loop kinematic feedback stage further refines the camera head while preserving the reconstructed scene geometry. To support training and evaluation, we curate EE4D-JSM from EgoExo4D by aligning egocentric video, sparse metric scene geometry, camera trajectories, and full-body motion annotations. Experiments show that RESELF outperforms state-of-the-art methods designed for the individual tasks across depth estimation, camera tracking, and full-body motion estimation. Code, models, and datasets will be available at https://ka1guan.github.io/RESELF/.