Optimizing an existing monocular 3D biomechanics pipeline for CPU hardware delivers 2.47x higher throughput and 59.6% shorter runtime while keeping joint-angle outputs nearly identical to the GPU baseline.
Monocu- larbiomechanics: Markerless biomechanics estimation from monocular video.https : / / github
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CPU Optimization of a Monocular 3D Biomechanics Pipeline for Low-Resource Deployment
Optimizing an existing monocular 3D biomechanics pipeline for CPU hardware delivers 2.47x higher throughput and 59.6% shorter runtime while keeping joint-angle outputs nearly identical to the GPU baseline.