Improving Video Colorization by Test-Time Tuning
This work addresses overfitting issues in video colorization for researchers and practitioners, but it is incremental as it builds on existing propagation methods.
The paper tackles the problem of overfitting in video colorization by proposing a test-time tuning method that uses the reference frame to create additional training samples during testing, resulting in an average performance boost of 1-3 dB in PSNR compared to the baseline.
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