Prompt-based test-time real image dehazing: a novel pipeline

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zixuan, He, Zewei, Lu, Ziqian, Sun, Xuecheng, Lu, Zhe-Ming
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913564461105152
author Chen, Zixuan
He, Zewei
Lu, Ziqian
Sun, Xuecheng
Lu, Zhe-Ming
author_facet Chen, Zixuan
He, Zewei
Lu, Ziqian
Sun, Xuecheng
Lu, Zhe-Ming
contents Existing methods attempt to improve models' generalization ability on real-world hazy images by exploring well-designed training schemes (\eg, CycleGAN, prior loss). However, most of them need very complicated training procedures to achieve satisfactory results. For the first time, we present a novel pipeline called Prompt-based Test-Time Dehazing (PTTD) to help generate visually pleasing results of real-captured hazy images during the inference phase. We experimentally observe that given a dehazing model trained on synthetic data, fine-tuning the statistics (\ie, mean and standard deviation) of encoding features is able to narrow the domain gap, boosting the performance of real image dehazing. Accordingly, we first apply a prompt generation module (PGM) to generate a visual prompt, which is the reference of appropriate statistical perturbations for mean and standard deviation. Then, we employ a feature adaptation module (FAM) into the existing dehazing models for adjusting the original statistics with the guidance of the generated prompt. PTTD is model-agnostic and can be equipped with various state-of-the-art dehazing models trained on synthetic hazy-clean pairs to tackle the real image dehazing task. Extensive experimental results demonstrate that our PTTD is effective, achieving superior performance against state-of-the-art dehazing methods in real-world scenarios. The code is available at \url{https://github.com/cecret3350/PTTD-Dehazing}.
format Preprint
id arxiv_https___arxiv_org_abs_2309_17389
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Prompt-based test-time real image dehazing: a novel pipeline
Chen, Zixuan
He, Zewei
Lu, Ziqian
Sun, Xuecheng
Lu, Zhe-Ming
Computer Vision and Pattern Recognition
Existing methods attempt to improve models' generalization ability on real-world hazy images by exploring well-designed training schemes (\eg, CycleGAN, prior loss). However, most of them need very complicated training procedures to achieve satisfactory results. For the first time, we present a novel pipeline called Prompt-based Test-Time Dehazing (PTTD) to help generate visually pleasing results of real-captured hazy images during the inference phase. We experimentally observe that given a dehazing model trained on synthetic data, fine-tuning the statistics (\ie, mean and standard deviation) of encoding features is able to narrow the domain gap, boosting the performance of real image dehazing. Accordingly, we first apply a prompt generation module (PGM) to generate a visual prompt, which is the reference of appropriate statistical perturbations for mean and standard deviation. Then, we employ a feature adaptation module (FAM) into the existing dehazing models for adjusting the original statistics with the guidance of the generated prompt. PTTD is model-agnostic and can be equipped with various state-of-the-art dehazing models trained on synthetic hazy-clean pairs to tackle the real image dehazing task. Extensive experimental results demonstrate that our PTTD is effective, achieving superior performance against state-of-the-art dehazing methods in real-world scenarios. The code is available at \url{https://github.com/cecret3350/PTTD-Dehazing}.
title Prompt-based test-time real image dehazing: a novel pipeline
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.17389