NCST: Neural-based Color Style Transfer for Video Retouching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xintao, Chen, Yaosen, Zhang, Siqin, Wang, Wei, Wen, Xuming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913569588641792
author Jiang, Xintao
Chen, Yaosen
Zhang, Siqin
Wang, Wei
Wen, Xuming
author_facet Jiang, Xintao
Chen, Yaosen
Zhang, Siqin
Wang, Wei
Wen, Xuming
contents Video color style transfer aims to transform the color style of an original video by using a reference style image. Most existing methods employ neural networks, which come with challenges like opaque transfer processes and limited user control over the outcomes. Typically, users cannot fine-tune the resulting images or videos. To tackle this issue, we introduce a method that predicts specific parameters for color style transfer using two images. Initially, we train a neural network to learn the corresponding color adjustment parameters. When applying style transfer to a video, we fine-tune the network with key frames from the video and the chosen style image, generating precise transformation parameters. These are then applied to convert the color style of both images and videos. Our experimental results demonstrate that our algorithm surpasses current methods in color style transfer quality. Moreover, each parameter in our method has a specific, interpretable meaning, enabling users to understand the color style transfer process and allowing them to perform manual fine-tuning if desired.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00335
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NCST: Neural-based Color Style Transfer for Video Retouching
Jiang, Xintao
Chen, Yaosen
Zhang, Siqin
Wang, Wei
Wen, Xuming
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
Image and Video Processing
Video color style transfer aims to transform the color style of an original video by using a reference style image. Most existing methods employ neural networks, which come with challenges like opaque transfer processes and limited user control over the outcomes. Typically, users cannot fine-tune the resulting images or videos. To tackle this issue, we introduce a method that predicts specific parameters for color style transfer using two images. Initially, we train a neural network to learn the corresponding color adjustment parameters. When applying style transfer to a video, we fine-tune the network with key frames from the video and the chosen style image, generating precise transformation parameters. These are then applied to convert the color style of both images and videos. Our experimental results demonstrate that our algorithm surpasses current methods in color style transfer quality. Moreover, each parameter in our method has a specific, interpretable meaning, enabling users to understand the color style transfer process and allowing them to perform manual fine-tuning if desired.
title NCST: Neural-based Color Style Transfer for Video Retouching
topic Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
Image and Video Processing
url https://arxiv.org/abs/2411.00335