Papers › EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation

EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation

26 Mar 2024arXiv:2403.18080archive 2025-07-28

Chenhongyi Yang, Anastasia Tkach, Shreyas Hampali, Linguang Zhang, Elliot J. Crowley, Cem Keskin

We present EgoPoseFormer, a simple yet effective transformer-based model for stereo egocentric human pose estimation. The main challenge in egocentric pose estimation is overcoming joint invisibility, which is caused by self-occlusion or a limited field of view (FOV) of head-mounted cameras. Our approach overcomes this challenge by incorporating a two-stage pose estimation paradigm: in the first stage, our model leverages the global information to estimate each joint's coarse location, then in the second stage, it employs a DETR style transformer to refine the coarse locations by exploiting fine-grained stereo visual features. In addition, we present a Deformable Stereo Attention operation to enable our transformer to effectively process multi-view features, which enables it to accurately localize each joint in the 3D world. We evaluate our method on the stereo UnrealEgo dataset and show it significantly outperforms previous approaches while being computationally efficient: it improves MPJPE by 27.4mm (45% improvement) with only 7.9% model parameters and 13.1% FLOPs compared to the state-of-the-art. Surprisingly, with proper training settings, we find that even our first-stage pose proposal network can achieve superior performance compared to previous arts. We also show that our method can be seamlessly extended to monocular settings, which achieves state-of-the-art performance on the SceneEgo dataset, improving MPJPE by 25.5mm (21% improvement) compared to the best existing method with only 60.7% model parameters and 36.4% FLOPs. Code is available at: https://github.com/ChenhongyiYang/egoposeformer .

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

chenhongyiyang/egoposeformer officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Human Pose Estimation Egocentric Pose Estimation Pose Estimation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Egocentric Pose Estimation	SceneEgo	EgoPoseFormer	Average MPJPE (mm)	93.0	#3 of 8	Archive leaderboard	report
Egocentric Pose Estimation	SceneEgo	EgoPoseFormer	PA-MPJPE	74.3	#3 of 8	Archive leaderboard	report
Egocentric Pose Estimation	UnrealEgo	EgoPoseFormer	Average MPJPE (mm)	33.4	#1 of 6	Archive leaderboard	report
Egocentric Pose Estimation	UnrealEgo	EgoPoseFormer	PA-MPJPE	32.7	#1 of 6	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Detr Dropout Feedforward Network Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections