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

05/19/2021
by   Jie Liang, et al.
0

Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps. In this paper, we focus on speeding-up the high-resolution photorealistic I2IT tasks based on closed-form Laplacian pyramid decomposition and reconstruction. Specifically, we reveal that the attribute transformations, such as illumination and color manipulation, relate more to the low-frequency component, while the content details can be adaptively refined on high-frequency components. We consequently propose a Laplacian Pyramid Translation Network (LPTN) to simultaneously perform these two tasks, where we design a lightweight network for translating the low-frequency component with reduced resolution and a progressive masking strategy to efficiently refine the high-frequency ones. Our model avoids most of the heavy computation consumed by processing high-resolution feature maps and faithfully preserves the image details. Extensive experimental results on various tasks demonstrate that the proposed method can translate 4K images in real-time using one normal GPU while achieving comparable transformation performance against existing methods. Datasets and codes are available: https://github.com/csjliang/LPTN.

READ FULL TEXT

page 1

page 3

page 6

page 7

research
01/31/2021

Deep Reformulated Laplacian Tone Mapping

Wide dynamic range (WDR) images contain more scene details and contrast ...
research
02/17/2022

Single UHD Image Dehazing via Interpretable Pyramid Network

Currently, most single image dehazing models cannot run an ultra-high-re...
research
03/15/2022

Multi-Curve Translator for Real-Time High-Resolution Image-to-Image Translation

The dominant image-to-image translation methods are based on fully convo...
research
08/05/2022

Low-Light Hyperspectral Image Enhancement

Due to inadequate energy captured by the hyperspectral camera sensor in ...
research
08/23/2022

Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization

While hematoxylin and eosin (H E) is a standard staining procedure, im...
research
08/26/2023

Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion

Vignetting commonly occurs as a degradation in images resulting from fac...
research
03/16/2020

Resolution Adaptive Networks for Efficient Inference

Recently, adaptive inference is gaining increasing attention due to its ...

Please sign up or login with your details

Forgot password? Click here to reset