An anatomy aware Mamba framework for video based 3D human pose estimation

Video-based 3D human pose estimation suffers from depth ambiguity and faces great challenges in modeling long‑range spatial and temporal dependencies. Diffusion models have emerged as a powerful paradigm for this task. However, their denoisers commonly rely on Transformer backbones, where quadratic self-attention complexity limits computational efficiency. We propose AnatoMamba, an anatomy-aware Mamba framework for diffusion-driven 3D human pose estimation. AnatoMamba employs Articulated Pyramid Pooling to aggregate multiscale body context, Kinematic Wave Scanning to serialize joints according to skeletal topology, and Anatomical Signature Injection to explicitly encode body-part membership. The derived anatomy-aware features are further refined through bidirectional spatial and temporal state space modeling to capture inter-joint dependencies and cross frame motion patterns. With 243-frame inputs and 10.44 million trainable parameters, AnatoMamba-L achieves an MPJPE of 38.5 mm on Human3.6M. In cross-dataset evaluation on MPI-INF-3DHP, it achieves 98.9% PCK, 87.5 AUC, and 14.7 mm MPJPE. These results demonstrate competitive pose estimation accuracy with a compact parameter footprint.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-16
DOI
https://doi.org/10.1038/s41598-026-80558-2
Primary Topic
Human Pose and Action Recognition
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An anatomy aware Mamba framework for video based 3D human pose estimation

Fangni Chen, Lili Zhong, Jiayi Song
2 links
Scientific Reports
Human Pose and Action Recognition
article

An anatomy aware Mamba framework for video based 3D human pose estimation

Fangni Chen, Lili Zhong, Jiayi Song
article en

Abstract

Video-based 3D human pose estimation suffers from depth ambiguity and faces great challenges in modeling long‑range spatial and temporal dependencies. Diffusion models have emerged as a powerful paradigm for this task. However, their denoisers commonly rely on Transformer backbones, where quadratic self-attention complexity limits computational efficiency. We propose AnatoMamba, an anatomy-aware Mamba framework for diffusion-driven 3D human pose estimation. AnatoMamba employs Articulated Pyramid Pooling to aggregate multiscale body context, Kinematic Wave Scanning to serialize joints according to skeletal topology, and Anatomical Signature Injection to explicitly encode body-part membership. The derived anatomy-aware features are further refined through bidirectional spatial and temporal state space modeling to capture inter-joint dependencies and cross frame motion patterns. With 243-frame inputs and 10.44 million trainable parameters, AnatoMamba-L achieves an MPJPE of 38.5 mm on Human3.6M. In cross-dataset evaluation on MPI-INF-3DHP, it achieves 98.9% PCK, 87.5 AUC, and 14.7 mm MPJPE. These results demonstrate competitive pose estimation accuracy with a compact parameter footprint.

Scientific Reports
Zhejiang University of Science and Technology (CN)
Human Pose and Action Recognition
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon