根据人眼视觉特性动态调整超分辨率，省算力不降画质。
Human Vision Constrained Super-Resolution
- 引入人眼视觉框架，按视觉敏感度动态指导超分过程。
- 在不损失观感质量前提下，降低2倍以上计算量（FLOPS）。
- 适合注重效率的图像视频处理应用，如移动端或实时系统。
现代深度学习超分辨率技术通常忽略内容特征和观看条件对人眼感知的影响。然而，人眼视觉系统（HVS）对图像细节的敏感度随空间频率、亮度、颜色、对比度及运动等因素变化，也受环境光照和观看距离影响。这表明：当合成细节超出人眼分辨能力时，额外计算资源即为浪费。为此，我们提出一种受人眼视觉启发、与网络结构无关的超分辨率控制方法，核心是显式的人类视觉处理框架（HVPF），可依据具体图像细节和观看条件，动态局部引导超分过程。通过结合网络分支设计，显著提升超分辨率方法的计算效率。定量与定性评估（含用户研究）证明，该方法可在不牺牲感知质量的前提下，将计算量（FLOPS）降低2倍及以上。
原文摘要 · Abstract (English)
Modern deep-learning super-resolution (SR) techniques process images and videos independently of the underlying content and viewing conditions. However, the sensitivity of the human visual system (HVS) to image details changes depending on the underlying image characteristics, such as spatial frequency, luminance, color, contrast, or motion; as well viewing condition aspects such as ambient lighting and distance to the display. This observation suggests that computational resources spent on up-sampling images/videos may be wasted whenever a viewer cannot resolve the synthesized details i.e the resolution of details exceeds the resolving capability of human vision. Motivated by this observation, we propose a human vision inspired and architecture-agnostic approach for controlling SR techniques to deliver visually optimal results while limiting computational complexity. Its core is an explicit Human Visual Processing Framework (HVPF) that dynamically and locally guides SR methods according to human sensitivity to specific image details and viewing conditions. We demonstrate the application of our framework in combination with network branching to improve the computational efficiency of SR methods. Quantitative and qualitative evaluations, including user studies, demonstrate the effectiveness of our approach in reducing FLOPS by factors of 2$\times$ and greater, without sacrificing perceived quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。