NCST: Neural-based Color Style Transfer for Video Retouching

TL;DR

This paper presents a neural network-based method for video color style transfer that offers interpretable parameters and allows user fine-tuning, improving transfer quality over existing methods.

Contribution

Introduces a neural network that predicts explicit, interpretable parameters for color style transfer, enabling better control and customization in video retouching.

Findings

Outperforms existing methods in transfer quality

Parameters have clear, interpretable meanings

Enables manual fine-tuning for desired results

Abstract

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.