# Segment Anything Model Meets Image Harmonization

Source: [Segment Anything Model Meets Image Harmonization](<https://www.sota2.com/research/paper/68fa71841e209131cea51b71>)

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

Data updated: 2025-10-26T02:08:33.784Z

Authors: Haoxing Chen, Yaohui Li, Zhangxuan Gu, Zhuoer Xu, Jun Lan, Huaxiong Li

Published: 2023-12-20T02:57:21.000Z

## Abstract

Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images. Current methods adopt either global-level or pixel-level feature matching. Global-level feature matching ignores the proximity prior, treating foreground and background as separate entities. On the other hand, pixel-level feature matching loses contextual information. Therefore, it is necessary to use the information from semantic maps that describe different objects to guide harmonization. In this paper, we propose Semantic-guided Region-aware Instance Normalization (SRIN) that can utilize the semantic segmentation maps output by a pre-trained Segment Anything Model (SAM) to guide the visual consistency learning of foreground and background features. Abundant experiments demonstrate the superiority of our method for image harmonization over state-of-the-art methods.

## 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/2312.12729>)

[PDF](<https://arxiv.org/pdf/2312.12729.pdf>)