Waterfall Transformer for Multi-person Pose Estimation
This work addresses pose estimation for computer vision applications, presenting an incremental improvement over existing transformer-based methods.
The paper tackles multi-person pose estimation by proposing the Waterfall Transformer architecture (WTPose), which uses a transformer-based waterfall module to generate multi-scale features and capture context, resulting in improved performance on the COCO dataset compared to other transformer architectures.
We propose the Waterfall Transformer architecture for Pose estimation (WTPose), a single-pass, end-to-end trainable framework designed for multi-person pose estimation. Our framework leverages a transformer-based waterfall module that generates multi-scale feature maps from various backbone stages. The module performs filtering in the cascade architecture to expand the receptive fields and to capture local and global context, therefore increasing the overall feature representation capability of the network. Our experiments on the COCO dataset demonstrate that the proposed WTPose architecture, with a modified Swin backbone and transformer-based waterfall module, outperforms other transformer architectures for multi-person pose estimation