WTPose: Waterfall Transformer for Multi-person Pose Estimation

Navin Ranjan, Bruno Artacho, Andreas Savakis; Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, 2025, pp. 1364-1371

Abstract


Human pose estimation is an important problem with broad applications that can be particularly useful for privacy preservation when analyzing activities and human-object interactions..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.

Related Material


[pdf]
[bibtex]
@InProceedings{Ranjan_2025_WACV, author = {Ranjan, Navin and Artacho, Bruno and Savakis, Andreas}, title = {WTPose: Waterfall Transformer for Multi-person Pose Estimation}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops}, month = {February}, year = {2025}, pages = {1364-1371} }