DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation

TL;DR

DeciWatch introduces a lightweight, sparse sampling framework for video-based 2D/3D human pose estimation that significantly improves efficiency by processing only a small fraction of frames without sacrificing accuracy.

Contribution

It presents a novel sample-denoise-recover framework that leverages sparse frame sampling and Transformer architectures to enhance efficiency in pose estimation tasks.

Findings

Achieves 10x efficiency improvement over existing methods.

Maintains comparable accuracy with full-frame processing.

Validated on multiple datasets and tasks.

Abstract

This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch. Unlike current solutions that estimate each frame in a video, DeciWatch introduces a simple yet effective sample-denoise-recover framework that only watches sparsely sampled frames, taking advantage of the continuity of human motions and the lightweight pose representation. Specifically, DeciWatch uniformly samples less than 10% video frames for detailed estimation, denoises the estimated 2D/3D poses with an efficient Transformer architecture, and then accurately recovers the rest of the frames using another Transformer-based network. Comprehensive experimental results on three video-based human pose estimation and body mesh recovery tasks with four datasets validate the efficiency and effectiveness of DeciWatch. Code is available at https://github.com/cure-lab/DeciWatch.