Blind Video Bit-Depth Expansion

Panjun Duan, Yang Zhao, Yuan Chen, Wei Jia, Zhao Zhang, Ronggang Wang

Abstract: With the rapid development of high-bit-depth display devices, bit-depth expansion (BDE) algorithms that extend low-bit-depth images to high-bit-depth images have received increasing attention. Due to the sensitivity of bit-depth distortions to tiny numerical changes in the least significant bits, the nuanced degradation differences in the training process may lead to varying degradation data distributions, causing the trained models to overfit specific types of degradations. This paper focuses on the problem of blind video BDE, proposing a degradation prediction and embedding framework, and designing a video BDE network based on a recurrent structure and dual-frame alignment fusion. Experimental results demonstrate that the proposed model can outperform some state-of-the-art (SOTA) models in terms of banding artifact removal and color correction, avoiding overfitting to specific degradations and obtaining better generalization ability across multiple datasets. The proposed degradation model and source codes will be open-sourced.

Primary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: Visual media represented by images or videos plays a crucial role in multimedia processing. However, with the development of high-bit-depth devices, current 8bit visual media require bit-depth expansion to recover high-bit-depth data. This paper proposes a blind video bit-depth expansion algorithm based on multiple degradation distributions, which can address the issue of poor generalization and robustness of current video bit-depth expansion methods. The proposed method is applicable to multiple multimedia tasks and can process existing visual media data to support current and future high-bit-depth devices.

Submission Number: 3342