Single UHD Image Dehazing via Interpretable Pyramid Network

02/17/2022
by   Boxue Xiao, et al.
9

Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time. To address the problem, we introduce the principle of infinite approximation of Taylor's theorem with the Laplace pyramid pattern to build a model which is capable of handling 4K hazy images in real-time. The N branch networks of the pyramid network correspond to the N constraint terms in Taylor's theorem. Low-order polynomials reconstruct the low-frequency information of the image (e.g. color, illumination). High-order polynomials regress the high-frequency information of the image (e.g. texture). In addition, we propose a Tucker reconstruction-based regularization term that acts on each branch network of the pyramid model. It further constrains the generation of anomalous signals in the feature space. Extensive experimental results demonstrate that our approach can not only run 4K images with haze in real-time on a single GPU (80FPS) but also has unparalleled interpretability. The developed method achieves state-of-the-art (SOTA) performance on two benchmarks (O/I-HAZE) and our updated 4KID dataset while providing the reliable groundwork for subsequent optimization schemes.

READ FULL TEXT

page 3

page 4

page 6

page 7

page 8

research
05/19/2021

High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network

Existing image-to-image translation (I2IT) methods are either constraine...
research
05/25/2021

High-Frequency aware Perceptual Image Enhancement

In this paper, we introduce a novel deep neural network suitable for mul...
research
04/11/2022

Pyramid Grafting Network for One-Stage High Resolution Saliency Detection

Recent salient object detection (SOD) methods based on deep neural netwo...
research
05/03/2017

Super-Resolution of Wavelet-Encoded Images

Multiview super-resolution image reconstruction (SRIR) is often cast as ...
research
07/24/2018

LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction

This paper addresses the single-image compressive sensing (CS) and recon...
research
05/21/2021

Pyramid Fusion Dark Channel Prior for Single Image Dehazing

In this paper, we propose the pyramid fusion dark channel prior (PF-DCP)...
research
01/09/2017

Green-Blue Stripe Pattern for Range Sensing from a Single Image

In this paper, we present a novel method for rapid high-resolution range...

Please sign up or login with your details

Forgot password? Click here to reset