2D Human Pose Estimation: New Benchmark and State of the Art Analysis

TLDR

Human pose estimation has advanced rapidly, yet existing datasets lack comprehensive coverage of pose challenges and remain the primary benchmark for training and evaluation. The paper introduces the MPII Human Pose benchmark, aiming to provide a more diverse and challenging dataset to spur future human body model development. The MPII dataset comprises over 800 activity categories, diverse viewpoints, detailed joint, 3D torso and head orientation, occlusion, and activity labels, along with adjacent video frames to support motion analysis. Using the dataset, the authors analyze state‑of‑the‑art pose estimation methods, revealing key strengths and weaknesses.

Abstract

Human pose estimation has made significant progress during the last years. However current datasets are limited in their coverage of the overall pose estimation challenges. Still these serve as the common sources to evaluate, train and compare different models on. In this paper we introduce a novel benchmark "MPII Human Pose" that makes a significant advance in terms of diversity and difficulty, a contribution that we feel is required for future developments in human body models. This comprehensive dataset was collected using an established taxonomy of over 800 human activities [1]. The collected images cover a wider variety of human activities than previous datasets including various recreational, occupational and householding activities, and capture people from a wider range of viewpoints. We provide a rich set of labels including positions of body joints, full 3D torso and head orientation, occlusion labels for joints and body parts, and activity labels. For each image we provide adjacent video frames to facilitate the use of motion information. Given these rich annotations we perform a detailed analysis of leading human pose estimation approaches and gaining insights for the success and failures of these methods.