AI 中文总结
针对现有超分辨率方法忽略退化因素导致计算分配不佳的问题，提出DPAMixerSR框架，通过感知退化排序模块路由图像块至自适应稀疏处理或轻量级卷积分支，实现高效且保真的超分辨率重建。
AI 中文摘要
尽管内容自适应方案在图像超分辨率（SR）方面取得了显著进展，但现有方法通常侧重于纹理复杂度，而忽略了内在的退化因素（如模糊核或噪声模式），导致计算分配和重建性能次优。为解决这一问题，我们提出了DPAMixerSR，一种退化模式感知框架，通过自适应稀疏计算实现高效超分辨率。我们设计了一个轻量级的感知退化排序（PDR）模块，将图像划分为严重退化和轻度退化的图像块，分别路由到自适应稀疏处理（ASP）和轻量级卷积分支。ASP执行结构对齐的多尺度稀疏传播和双向细化，而卷积分支在轻度退化区域提高效率。通过将退化驱动的路由与结构对齐的稀疏处理相结合，DPAMixerSR建立了一个自调节框架，动态平衡计算效率和重建保真度。在各种SR任务上的大量实验表明，我们的DPAMixerSR在显著降低计算开销的同时实现了优越的结构恢复和感知保真度，为退化感知、资源高效的SR提供了一种新颖且可扩展的框架。
英文摘要
While content-adaptive schemes have delivered notable advances in image super-resolution (SR), existing approaches typically focus on texture complexity and ignore intrinsic degradation factors (e.g., blur kernels or noise patterns), leading to suboptimal computation allocation and reconstruction performance. To remedy this, we propose DPAMixerSR, a degradation-pattern-aware framework that enables efficient SR through adaptive sparse computation. We design a lightweight Perceptual Degradation Ranking (PDR) module partitions the image into severely and mildly degraded patches, which are routed to the Adaptive Sparse Processing (ASP) and a lightweight convolutional branch, respectively. ASP performs structure-aligned, multi-scale sparse propagation and bidirectional refinement, while the convolutional branch enhances efficiency in mildly degraded regions. By coupling degradation-driven routing with structure-aligned sparse processing, DPAMixerSR establishes a self-regulating framework that dynamically balances computational efficiency and reconstruction fidelity. Extensive experiments on various SR tasks demonstrate that our DPAMixerSR achieves superior structural restoration and perceptual fidelity with markedly reduced computational overhead, providing a novel and scalable framework for degradation-aware, resource-efficient SR.
CommentsPRCV2026
