Region-Adaptive Video Sharpening via Rate-Perception Optimization
This addresses video quality and compression efficiency for video processing applications, but is incremental as it builds on existing sharpening and coding techniques.
The paper tackled the problem of uniform sharpening degrading video quality and increasing bitrate by proposing RPO-AdaSharp, a region-adaptive model that uses CTU partition masks to allocate bits, achieving perceptual enhancement and bitrate savings as demonstrated in benchmarks.
Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques to optimally allocate these additional bits across diverse regions. Thus, this paper proposes RPO-AdaSharp, an end-to-end region-adaptive video sharpening model for both perceptual enhancement and bitrate savings. We use the coding tree unit (CTU) partition mask as prior information to guide and constrain the allocation of increased bits. Experiments on benchmarks demonstrate the effectiveness of the proposed model qualitatively and quantitatively.