Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation

TL;DR

This paper introduces the MGIL model for low-resolution human pose estimation, replacing downsampling layers with multi-granular, lossless, and structural information modules to improve accuracy in challenging low-res scenarios.

Contribution

The paper proposes a novel MGIL framework with FLIE, CII, and MGAF modules to effectively utilize structural and multi-granular information, addressing limitations of existing models on low-resolution images.

Findings

Outperforms SOTA by 7.7 mAP on COCO

Effective across various resolutions and backbones

Enhances low-resolution pose estimation accuracy

Abstract

In real-world applications of human pose estimation, low-resolution input images are frequently encountered when the performance of the image acquisition equipment is limited or the shooting distance is too far. However, existing state-of-the-art models for human pose estimation perform poorly on low-resolution images. One key reason is the presence of downsampling layers in these models, e.g., strided convolutions and pooling layers. It further reduces the already insufficient image information. Another key reason is that the body skeleton and human kinematic information are not fully utilized. In this work, we propose a Multi-Granular Information-Lossless (MGIL) model to replace the downsampling layers to address the above issues. Specifically, MGIL employs a Fine-grained Lossless Information Extraction (FLIE) module, which can prevent the loss of local information. Furthermore, we design a Coarse-grained Information Interaction (CII) module to adequately leverage human body structural information. To efficiently fuse cross-granular information and thoroughly exploit the relationships among keypoints, we further introduce a Multi-Granular Adaptive Fusion (MGAF) mechanism. The mechanism assigns weights to features of different granularities based on the content of the image. The model is effective, flexible, and universal. We show its potential in various vision tasks with comprehensive experiments. It outperforms the SOTA methods by 7.7 mAP on COCO and performs well with different input resolutions, different backbones, and different vision tasks. The code is provided in supplementary material.