AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild

TL;DR

AdaFuse is an adaptive multiview fusion method that improves human pose estimation in occluded scenarios by leveraging visible views and learning adaptive fusion weights, outperforming state-of-the-art methods across multiple datasets.

Contribution

The paper introduces AdaFuse, a novel adaptive multiview fusion approach that enhances feature quality in occluded views for accurate pose estimation without additional sensors.

Findings

Outperforms state-of-the-art on Human3.6M, Total Capture, and CMU Panoptic datasets.

Effectively determines point correspondences using heatmap sparsity.

Provides a new synthetic dataset Occlusion-Person for occlusion evaluation.

Abstract

Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views. The core of AdaFuse is to determine the point-point correspondence between two views which we solve effectively by exploring the sparsity of the heatmap representation. We also learn an adaptive fusion weight for each camera view to reflect its feature quality in order to reduce the chance that good features are undesirably corrupted by ``bad'' views. The fusion model is trained end-to-end with the pose estimation network, and can be directly applied to new camera configurations without additional adaptation. We extensively evaluate the approach on three public datasets including Human3.6M, Total Capture and CMU Panoptic. It outperforms the state-of-the-arts on all of them. We also create a large scale synthetic dataset Occlusion-Person, which allows us to perform numerical evaluation on the occluded joints, as it provides occlusion labels for every joint in the images. The dataset and code are released at https://github.com/zhezh/adafuse-3d-human-pose.