探索通过测试时间训练的高效图像恢复
Exploring Diffusion with Test-Time Training on Efficient Image Restoration
AI总结：
DiffRWKVIR通过结合测试时间训练与高效扩散，实现了高效的图像恢复，在多个基准测试中表现出色。
摘要：
图像恢复面临诸多挑战，包括特征融合无效、计算瓶颈以及扩散过程低效。为了解决这些问题，我们提出了DiffRWKVIR，一种将测试时间训练（TTT）与高效扩散相结合的新型框架。我们的方法引入了三个关键创新：（1） Omni-Scale 2D状态演变扩展了RWKV的位置依赖参数化，使其适用于层次化的多方向二维扫描，从而通过线性复杂度O(L)实现全局上下文意识；（2） Chunk-Optimized Flash处理通过连续块处理（复杂度O(LCd））将块内并行性加速了3.2倍，减少了序列依赖性和计算开销；（3） Prior-Guided Efficient Diffusion在仅5-20步内提取出紧凑的图像先验表示（IPR），证明其在训练/推理速度上比DiffIR快45%，同时解决了去噪中的计算低效问题。在超分辨率和修复基准（Set5、Set14、BSD100、Urban100、Places365）上进行评估，DiffRWKVIR在PSNR、SSIM、LPIPS和效率指标上均优于SwinIR、HAT和MambaIR/v2。我们的方法建立了一种新的适应性、高效率图像恢复范式，通过优化硬件利用率。
英文摘要：
Image restoration faces challenges including ineffective feature fusion, computational bottlenecks and inefficient diffusion processes. To address these, we propose DiffRWKVIR, a novel framework unifying Test-Time Training (TTT) with efficient diffusion. Our approach introduces three key innovations: (1) Omni-Scale 2D State Evolution extends RWKV's location-dependent parameterization to hierarchical multi-directional 2D scanning, enabling global contextual awareness with linear complexity O(L); (2) Chunk-Optimized Flash Processing accelerates intra-chunk parallelism by 3.2x via contiguous chunk processing (O(LCd) complexity), reducing sequential dependencies and computational overhead; (3) Prior-Guided Efficient Diffusion extracts a compact Image Prior Representation (IPR) in only 5-20 steps, proving 45% faster training/inference than DiffIR while solving computational inefficiency in denoising. Evaluated across super-resolution and inpainting benchmarks (Set5, Set14, BSD100, Urban100, Places365), DiffRWKVIR outperforms SwinIR, HAT, and MambaIR/v2 in PSNR, SSIM, LPIPS, and efficiency metrics. Our method establishes a new paradigm for adaptive, high-efficiency image restoration with optimized hardware utilization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
