Efficient Multi-Person Pose Estimation with Provable Guarantees

TL;DR

This paper presents a novel bottom-up method for multi-person pose estimation that formulates the problem as a set packing task, employing an efficient algorithm with provable guarantees to achieve near-optimal solutions.

Contribution

It introduces a new algorithm combining implicit column generation and nested Bender's decomposition to efficiently solve the MWSP problem with provable bounds for MPPE.

Findings

Achieves comparable accuracy to state-of-the-art methods on MPII-Multiperson dataset.

Provides globally optimal solutions for over 99% of instances, with bounds for others.

Speeds up inference significantly compared to naive dynamic programming.

Abstract

Multi-person pose estimation (MPPE) in natural images is key to the meaningful use of visual data in many fields including movement science, security, and rehabilitation. In this paper we tackle MPPE with a bottom-up approach, starting with candidate detections of body parts from a convolutional neural network (CNN) and grouping them into people. We formulate the grouping of body part detections into people as a minimum-weight set packing (MWSP) problem where the set of potential people is the power set of body part detections. We model the quality of a hypothesis of a person which is a set in the MWSP by an augmented tree-structured Markov random field where variables correspond to body-parts and their state-spaces correspond to the power set of the detections for that part. We describe a novel algorithm that combines efficiency with provable bounds on this MWSP problem. We employ an implicit column generation strategy where the pricing problem is formulated as a dynamic program. To efficiently solve this dynamic program we exploit the problem structure utilizing a nested Bender's decomposition (NBD) exact inference strategy which we speed up by recycling Bender's rows between calls to the pricing problem. We test our approach on the MPII-Multiperson dataset, showing that our approach obtains comparable results with the state-of-the-art algorithm for joint node labeling and grouping problems, and that NBD achieves considerable speed-ups relative to a naive dynamic programming approach. Typical algorithms that solve joint node labeling and grouping problems use heuristics and thus can not obtain proofs of optimality. Our approach, in contrast, proves that for over 99 percent of problem instances we find the globally optimal solution and otherwise provide upper/lower bounds.