Towards Accurate Markerless Human Shape and Pose Estimation over Time

TL;DR

This paper presents an automatic multi-view video method for accurate 3D human shape and pose estimation that overcomes common limitations like background assumptions and static cameras, using CNN segmentation and temporal priors.

Contribution

It extends the SMPLify framework with multi-view fitting, CNN-based segmentation, and a DCT temporal prior, enabling more accurate and versatile 3D human motion capture.

Findings

Results are comparable to state-of-the-art methods.

Provides realistic 3D shape avatars.

Effective on monocular sequences from YouTube.

Abstract

Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios. Here we propose a fully automatic method that given multi-view video, estimates 3D human motion and body shape. We take recent SMPLify \cite{bogo2016keep} as the base method, and extend it in several ways. First we fit the body to 2D features detected in multi-view images. Second, we use a CNN method to segment the person in each image and fit the 3D body model to the contours to further improves accuracy. Third we utilize a generic and robust DCT temporal prior to handle the left and right side swapping issue sometimes introduced by the 2D pose estimator. Validation on standard benchmarks shows our results are comparable to the state of the art and also provide a realistic 3D shape avatar. We also demonstrate accurate results on HumanEva and on challenging dance sequences from YouTube in monocular case.