Improving Video Colorization by Test-Time Tuning

TL;DR

This paper introduces a test-time tuning method for video colorization that improves performance by leveraging reference frames to adapt models during testing, resulting in significant PSNR gains.

Contribution

The proposed approach enhances video colorization by enabling test-time adaptation using reference frames, reducing overfitting and improving testing performance.

Findings

Achieves 1-3 dB PSNR improvement over baseline.

Utilizes reference frames for test-time training.

Code available at provided URL.

Abstract

With the advancements in deep learning, video colorization by propagating color information from a colorized reference frame to a monochrome video sequence has been well explored. However, the existing approaches often suffer from overfitting the training dataset and sequentially lead to suboptimal performance on colorizing testing samples. To address this issue, we propose an effective method, which aims to enhance video colorization through test-time tuning. By exploiting the reference to construct additional training samples during testing, our approach achieves a performance boost of 1~3 dB in PSNR on average compared to the baseline. Code is available at: https://github.com/IndigoPurple/T3