3D human pose estimation with adaptive receptive fields and dilated temporal convolutions
This work addresses computational efficiency in pose estimation for video analysis, though it is incremental as it builds on existing methods with specific optimizations.
The paper tackled 3D human pose estimation by introducing adaptive receptive fields based on optical flow to improve efficiency, achieving a 23% faster processing speed for slow-motion sequences while maintaining pose prediction accuracy within 0.36% of the benchmark model.
In this work, we demonstrate that receptive fields in 3D pose estimation can be effectively specified using optical flow. We introduce adaptive receptive fields, a simple and effective method to aid receptive field selection in pose estimation models based on optical flow inference. We contrast the performance of a benchmark state-of-the-art model running on fixed receptive fields with their adaptive field counterparts. By using a reduced receptive field, our model can process slow-motion sequences (10x longer) 23% faster than the benchmark model running at regular speed. The reduction in computational cost is achieved while producing a pose prediction accuracy to within 0.36% of the benchmark model.