# Lightweight high-resolution Subject Matting in the Real World

Source: [Lightweight high-resolution Subject Matting in the Real World](<https://www.sota2.com/research/paper/68fa717c1e209131cea518d8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:03.221Z

Authors: Peng Liu, Fanyi Wang, Jingwen Su, Yanhao Zhang, Guojun Qi

Published: 2023-12-12T09:27:57.000Z

## Abstract

Existing saliency object detection (SOD) methods struggle to satisfy fast inference and accurate results simultaneously in high resolution scenes. They are limited by the quality of public datasets and efficient network modules for high-resolution images. To alleviate these issues, we propose to construct a saliency object matting dataset HRSOM and a lightweight network PSUNet. Considering efficient inference of mobile depolyment framework, we design a symmetric pixel shuffle module and a lightweight module TRSU. Compared to 13 SOD methods, the proposed PSUNet has the best objective performance on the high-resolution benchmark dataset. Evaluation results of objective assessment are superior compared to U$^2$Net that has 10 times of parameter amount of our network. On Snapdragon 8 Gen 2 Mobile Platform, inference a single 640$\\times$640 image only takes 113ms. And on the subjective assessment, evaluation results are better than the industry benchmark IOS16 (Lift subject from background).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.07100>)

[PDF](<https://arxiv.org/pdf/2312.07100.pdf>)
