Exploiting Offset-guided Network for Pose Estimation and Tracking
This work addresses a specific bottleneck in pose estimation for computer vision applications, representing an incremental improvement.
The paper tackles quantization errors in human pose estimation by proposing an Offset-guided Network (OGN) with a fusion strategy, achieving state-of-the-art results on COCO and PoseTrack datasets.
Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location heatmaps, which causes quantization errors and inevitably deteriorates the performance within the reduced network output. Aim at solving it, we revisit the heatmap-offset aggregation method and propose the Offset-guided Network (OGN) with an intuitive but effective fusion strategy for both two-stages pose estimation and Mask R-CNN. For two-stages pose estimation, a greedy box generation strategy is also proposed to keep more necessary candidates while performing person detection. For mask R-CNN, ratio-consistent is adopted to improve the generalization ability of the network. State-of-the-art results on COCO and PoseTrack dataset verify the effectiveness of our offset-guided pose estimation and tracking.