SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking

TL;DR

This paper introduces SIMSPINE, a large-scale dataset and simulation framework for biomechanically accurate 3D spine motion annotation, enabling improved computer vision models for spine analysis in natural human movements.

Contribution

It presents the first open dataset, SIMSPINE, with 3D spinal keypoints derived from musculoskeletal modeling, and provides baseline models and benchmarks for spine motion estimation.

Findings

2.14 million frames in the dataset enable data-driven vertebral kinematics learning.

State-of-the-art 2D spine detection AUC improved from 0.63 to 0.80.

In-the-wild spine tracking AP improved from 0.91 to 0.93.

Abstract

Modeling spinal motion is fundamental to understanding human biomechanics, yet remains underexplored in computer vision due to the spine's complex multi-joint kinematics and the lack of large-scale 3D annotations. We present a biomechanics-aware keypoint simulation framework that augments existing human pose datasets with anatomically consistent 3D spinal keypoints derived from musculoskeletal modeling. Using this framework, we create the first open dataset, named SIMSPINE, which provides sparse vertebra-level 3D spinal annotations for natural full-body motions in indoor multi-camera capture without external restraints. With 2.14 million frames, this enables data-driven learning of vertebral kinematics from subtle posture variations and bridges the gap between musculoskeletal simulation and computer vision. In addition, we release pretrained baselines covering fine-tuned 2D detectors, monocular 3D pose lifting models, and multi-view reconstruction pipelines, establishing a unified benchmark for biomechanically valid spine motion estimation. Specifically, our 2D spine baselines improve the state-of-the-art from 0.63 to 0.80 AUC in controlled environments, and from 0.91 to 0.93 AP for in-the-wild spine tracking. Together, the simulation framework and SIMSPINE dataset advance research in vision-based biomechanics, motion analysis, and digital human modeling by enabling reproducible, anatomically grounded 3D spine estimation under natural conditions.