用3D注意力提升轻量图像超分辨率细节表现
CubeFormer: A Simple yet Effective Baseline for Lightweight Image Super-Resolution
- 引入3D立方体注意力，增强特征多样性
- 在多个基准上达到当前最优性能
- 适合追求高效高质图像重建的开发者
轻量级图像超分辨率方法旨在使用小型神经网络提升图像分辨率并恢复细节，但现有方法仍存在性能不足和细节不自然的问题。分析表明，受限的特征多样性是主要原因。为此，我们提出简单有效的基线模型CubeFormer，通过完整信息聚合增强特征丰富性。具体地，引入立方体注意力，将二维注意力扩展至三维空间，实现全面的信息交互，促进特征多样性和信息提取。此外，采用块采样与网格采样策略，构建局部建模的立方体内变换块（Intra-CTB）和全局建模的立方体间变换块（Inter-CTB）。大量实验表明，CubeFormer在常用超分辨率基准上达到当前最优性能。源代码与模型将公开发布。
原文摘要 · Abstract (English)
Lightweight image super-resolution (SR) methods aim at increasing the resolution and restoring the details of an image using a lightweight neural network. However, current lightweight SR methods still suffer from inferior performance and unpleasant details. Our analysis reveals that these methods are hindered by constrained feature diversity, which adversely impacts feature representation and detail recovery. To respond this issue, we propose a simple yet effective baseline called CubeFormer, designed to enhance feature richness by completing holistic information aggregation. To be specific, we introduce cube attention, which expands 2D attention to 3D space, facilitating exhaustive information interactions, further encouraging comprehensive information extraction and promoting feature variety. In addition, we inject block and grid sampling strategies to construct intra-cube transformer blocks (Intra-CTB) and inter-cube transformer blocks (Inter-CTB), which perform local and global modeling, respectively. Extensive experiments show that our CubeFormer achieves state-of-the-art performance on commonly used SR benchmarks. Our source code and models will be publicly available.
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。