针对高分辨率图像信息分布不均问题，提出分块动态缩放框架提升超分质量。
Block-Based Multi-Scale Image Rescaling
- 将图像分块后为每块分配动态缩放率，保持整体缩放比例不变。
- 在2K和4K数据集上显著提升超分图像质量，有效消除块状伪影。
- 适合处理2K以上高分辨率图像的超分辨率重建任务。
图像重缩放（IR）旨在确定高分辨率（HR）图像的最佳低分辨率（LR）表示，以重建高质量的超分辨率（SR）图像。通常，分辨率超过2K的HR图像包含丰富且分布不均的信息。传统方法仅关注整体缩放率，忽略图像各部分信息量差异，导致性能受限。为此，我们提出适用于2K及以上分辨率图像重缩放任务的基于块的多尺度框架（BBMR）。BBMR由下采样模块和上采样模块组成：下采样模块将HR图像分割为等大小子块，为每块动态分配缩放率，同时保持整体缩放率恒定；上采样模块引入联合超分辨率方法（JointSR），对不同缩放率的子块进行超分重建，有效消除块状伪影。实验表明，与初始网络图像重缩放方法相比，BBMR在2K和4K测试数据集上的超分图像质量显著提升。
原文摘要 · Abstract (English)
Image rescaling (IR) seeks to determine the optimal low-resolution (LR) representation of a high-resolution (HR) image to reconstruct a high-quality super-resolution (SR) image. Typically, HR images with resolutions exceeding 2K possess rich information that is unevenly distributed across the image. Traditional image rescaling methods often fall short because they focus solely on the overall scaling rate, ignoring the varying amounts of information in different parts of the image. To address this limitation, we propose a Block-Based Multi-Scale Image Rescaling Framework (BBMR), tailored for IR tasks involving HR images of 2K resolution and higher. BBMR consists of two main components: the Downscaling Module and the Upscaling Module. In the Downscaling Module, the HR image is segmented into sub-blocks of equal size, with each sub-block receiving a dynamically allocated scaling rate while maintaining a constant overall scaling rate. For the Upscaling Module, we introduce the Joint Super-Resolution method (JointSR), which performs SR on these sub-blocks with varying scaling rates and effectively eliminates blocking artifacts. Experimental results demonstrate that BBMR significantly enhances the SR image quality on the of 2K and 4K test dataset compared to initial network image rescaling methods.
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。