DeepAI AI Chat
Log In Sign Up

Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration

by   Jie Chen, et al.
City University of Hong Kong
Vivo Communication Technology Co. Ltd.
Hong Kong Baptist University
Nanyang Technological University
Agency for Science, Technology and Research

High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most modern imaging platforms. In spite of recent developments in both hardware and algorithm innovations, challenges remain over content association ambiguities caused by saturation, motion, and various artifacts introduced during multi-exposure fusion such as ghosting, noise, and blur. In this work, we propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model which aims to address these issues within one framework. An efficient two-stream structure is proposed which separately focuses on texture feature transfer over saturated regions and multi-exposure tonal and texture feature fusion. A neural feature transfer mechanism is proposed which establishes spatial correspondence between different exposures based on multi-scale VGG features in the masked saturated HDR domain for discriminative contextual clues over the ambiguous image areas. A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner. In addition, we introduce several novel attention mechanisms, i.e., the motion attention module detects and suppresses the content discrepancies among the reference images; the saturation attention module facilitates differentiating the misalignment caused by saturation from those caused by motion; and the scale attention module ensures texture blending consistency between different coder/decoder scales. We carry out comprehensive qualitative and quantitative evaluations and ablation studies, which validate that these novel modules work coherently under the same framework and outperform state-of-the-art methods.


page 1

page 3

page 4

page 7

page 8

page 9


ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging

In this paper, we present an attention-guided deformable convolutional n...

Multi-scale Dynamic Feature Encoding Network for Image Demoireing

The prevalence of digital sensors, such as digital cameras and mobile ph...

Wavelet-Based Network For High Dynamic Range Imaging

High dynamic range (HDR) imaging from multiple low dynamic range (LDR) i...

Attention-Guided NIR Image Colorization via Adaptive Fusion of Semantic and Texture Clues

Near infrared (NIR) imaging has been widely applied in low-light imaging...

Scale-aware Two-stage High Dynamic Range Imaging

Deep high dynamic range (HDR) imaging as an image translation issue has ...

Efficient Progressive High Dynamic Range Image Restoration via Attention and Alignment Network

HDR is an important part of computational photography technology. In thi...