# AG-EgoPose: Spatially Anchored Residual Correction with Action Context for Monocular Egocentric 3D Pose Estimation

arXiv: https://arxiv.org/abs/2603.25175 · HTML: https://mlsanity.com/paper/2603.25175/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 26 Mar 2026.

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

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (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)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Egocentric Video-Language Pretraining](https://mlsanity.com/paper/2206.01670/) (2022)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [Ego-Body Pose Estimation via Ego-Head Pose Estimation](https://mlsanity.com/paper/2212.04636/) (2022)
- [You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions](https://mlsanity.com/paper/1904.09882/) (2019)
- [xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera](https://mlsanity.com/paper/1907.10045/) (2019)
- [Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera](https://mlsanity.com/paper/1803.05959/) (2018)
- [Estimating Body and Hand Motion in an Ego-sensed World](https://mlsanity.com/paper/2410.03665/) (2024)
- [UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture](https://mlsanity.com/paper/2208.01633/) (2022)
- [Estimating Egocentric 3D Human Pose in Global Space](https://mlsanity.com/paper/2104.13454/) (2021)
- [SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera](https://mlsanity.com/paper/2011.01519/) (2020)
- [Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video](https://mlsanity.com/paper/1603.07763/) (2016)
- [Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision](https://mlsanity.com/paper/2201.07929/) (2022)
- [Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement](https://mlsanity.com/paper/2311.16495/) (2023)
- [Egocentric Pose Estimation from Human Vision Span](https://mlsanity.com/paper/2104.05167/) (2021)
- [Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views](https://mlsanity.com/paper/2309.11962/) (2023)
- [REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning](https://mlsanity.com/paper/2504.04956/) (2025)
- [Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting](https://mlsanity.com/paper/2402.18330/) (2024)
- [EgoCast: Forecasting Egocentric Human Pose in the Wild](https://mlsanity.com/paper/2412.02903/) (2024)
- [A Survey on 3D Egocentric Human Pose Estimation](https://mlsanity.com/paper/2403.17893/) (2024)
- [Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision](https://mlsanity.com/paper/2503.06089/) (2025)
- [EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR](https://mlsanity.com/paper/2603.04090/) (2026)
- [Egocentric Visibility-Aware Human Pose Estimation](https://mlsanity.com/paper/2602.23618/) (2026)

## Abstract (arXiv)

Monocular egocentric 3D pose estimation is difficult because severe foreshortening, self-occlusion, and a restricted field of view often remove the image evidence needed to recover the camera wearer's body. Temporal context can resolve these ambiguities, but unconstrained fusion may also corrupt joints that are already localized reliably from the current frame. We present AG-EgoPose, an action-guided framework that treats temporal information as a bounded-gate residual correction to a spatial pose estimate. A frozen heatmap network produces joint heatmaps and feature-pyramid features, from which a spatial transformer estimates an independently supervised 3D pose. The heatmaps further guide joint-local pooling of frozen DINOv2 patch tokens, while DINOv2 frame tokens are processed by an Ego4D-pretrained ActionFormer to obtain action-scale temporal context. Each spatial joint token, augmented with its local appearance feature, attends to the temporal sequence and predicts a zero-initialized 3D residual. A per-joint gate, derived from heatmap location and confidence statistics, bounds the residual weight. AG-EgoPose improves over the strongest evaluated baselines by 10.1% PA-MPJPE on EgoPW, and by 9.0% MPJPE and 6.3% PA-MPJPE on SceneEgo after fine-tuning. Code will be made publicly available at https://github.com/