StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
This addresses the need for customizable, real-time image enhancement tools for users and applications requiring aesthetic control, representing a novel method for a known bottleneck.
The paper tackles the problem of subjective image enhancement with varying user preferences by proposing StarEnhancer, a single deep learning model that can transform images between multiple tonal styles including unseen ones, achieving over 200 FPS on 4K-resolution images while surpassing contemporary single-style methods in PSNR, SSIM, and LPIPS metrics.
Image enhancement is a subjective process whose targets vary with user preferences. In this paper, we propose a deep learning-based image enhancement method covering multiple tonal styles using only a single model dubbed StarEnhancer. It can transform an image from one tonal style to another, even if that style is unseen. With a simple one-time setting, users can customize the model to make the enhanced images more in line with their aesthetics. To make the method more practical, we propose a well-designed enhancer that can process a 4K-resolution image over 200 FPS but surpasses the contemporaneous single style image enhancement methods in terms of PSNR, SSIM, and LPIPS. Finally, our proposed enhancement method has good interactability, which allows the user to fine-tune the enhanced image using intuitive options.