Saved in:
Bibliographic Details
Main Authors: Huang, Yue, Hu, Tianle, Chen, Yu, Li, Zi'ang, Wen, Jie, Fang, Xiaozhao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915797411037184
author Huang, Yue
Hu, Tianle
Chen, Yu
Li, Zi'ang
Wen, Jie
Fang, Xiaozhao
author_facet Huang, Yue
Hu, Tianle
Chen, Yu
Li, Zi'ang
Wen, Jie
Fang, Xiaozhao
contents Single image reflection separation aims to separate the transmission and reflection layers from a mixed image. Existing methods typically combine general priors from pre-trained models with task-specific priors such as text prompts and reflection detection. However, the transmission prior, as the most direct task-specific prior for the target transmission layer, has not been effectively modeled or fully utilized, limiting performance in complex scenarios. To address this issue, we propose a dual-prior interaction framework based on lightweight transmission prior generation and effective prior fusion. First, we design a Local Linear Correction Network (LLCN) that finetunes pre-trained models based on the physical constraint T=SI+B, where S and B represent pixel-wise and channel-wise scaling and bias transformations. LLCN efficiently generates high-quality transmission priors with minimal parameters. Second, we construct a Dual-Prior Interaction Transformer (DPIT) that employs a dual-stream channel reorganization attention mechanism. By reorganizing features from general and transmission priors for attention computation, DPIT achieves deep fusion of both priors, fully exploiting their complementary information. Experimental results on multiple benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12641
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Single Image Reflection Separation via Dual Prior Interaction Transformer
Huang, Yue
Hu, Tianle
Chen, Yu
Li, Zi'ang
Wen, Jie
Fang, Xiaozhao
Computer Vision and Pattern Recognition
Artificial Intelligence
Single image reflection separation aims to separate the transmission and reflection layers from a mixed image. Existing methods typically combine general priors from pre-trained models with task-specific priors such as text prompts and reflection detection. However, the transmission prior, as the most direct task-specific prior for the target transmission layer, has not been effectively modeled or fully utilized, limiting performance in complex scenarios. To address this issue, we propose a dual-prior interaction framework based on lightweight transmission prior generation and effective prior fusion. First, we design a Local Linear Correction Network (LLCN) that finetunes pre-trained models based on the physical constraint T=SI+B, where S and B represent pixel-wise and channel-wise scaling and bias transformations. LLCN efficiently generates high-quality transmission priors with minimal parameters. Second, we construct a Dual-Prior Interaction Transformer (DPIT) that employs a dual-stream channel reorganization attention mechanism. By reorganizing features from general and transmission priors for attention computation, DPIT achieves deep fusion of both priors, fully exploiting their complementary information. Experimental results on multiple benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.
title Single Image Reflection Separation via Dual Prior Interaction Transformer
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.12641