# Waterfall Transformer for Multi-person Pose Estimation

Source: [Waterfall Transformer for Multi-person Pose Estimation](<https://www.sota2.com/research/paper/68fa75e01e209131cea6a651>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:43:58.474Z

Authors: Navin Ranjan, Bruno Artacho, Andreas Savakis

Published: 2024-11-28T06:24:40.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.18944>)

[PDF](<https://arxiv.org/pdf/2411.18944.pdf>)