发表机构
Harbin Institute of Technology, Shenzhen; Tsinghua University; École Polytechnique Fédérale de Lausanne; Shenzhen University; Peng Cheng Laboratory（哈尔滨工业大学（深圳）; 清华大学; 洛桑联邦理工学院; 深圳大学; 鹏城实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图像恢复中静态参数难以适应实例特定退化的问题，提出TTTIR框架，通过渐进式状态序列生成和状态转移演化实现动态实例特定恢复，在多个基准上超越现有模型。
AI 中文摘要
图像恢复因其真实世界退化类型的多样性和高度输入依赖性而固有地具有挑战性。尽管最近的架构如Transformer和状态空间模型推动了该领域的发展，但它们主要依赖于静态的、全局共享的参数，这难以完全适应实例特定的退化模式。测试时训练（TTT）为生成数据相关的算子提供了一种有前景的范式，但其标准的自监督内循环缺乏将退化特征向干净结构过渡所需的显式指导。为解决这一问题，我们提出了TTTIR，一种将图像恢复重新表述为实例特定状态演化过程的新型框架。具体而言，我们设计了渐进式状态序列生成（PSSG）来构建互补的空间-频率目标状态（定义要恢复什么），以及状态转移演化（STE）通过面向恢复的TTT内循环（确定特征应如何演化）来适应轻量级转移算子。大量实验表明，TTTIR在多个图像恢复基准上持续优于最先进的模型，实现了具有良好计算可扩展性的动态实例特定恢复。代码可在以下网址获取：此https URL。
英文摘要
Image restoration is inherently challenging due to the diverse and highly input-dependent nature of real-world degradations. While recent architectures like Transformers and state-space models have advanced the field, they predominantly rely on static, globally shared parameters, which struggle to fully accommodate instance-specific degradation patterns. Test-Time Training (TTT) offers a promising paradigm for generating data-dependent operators, yet its standard self-supervised inner loop lacks the explicit guidance required to transition degraded features toward clean structures. To address this, we propose TTTIR, a novel framework that reformulates image restoration as an instance-specific state evolution process. Specifically, we design Progressive State Sequence Generation (PSSG) to construct complementary spatial-frequency target states (defining what to recover), and State Transition Evolution (STE) to adapt lightweight transition operators via a restoration-oriented TTT inner loop (determining how the features should evolve). Extensive experiments demonstrate that TTTIR consistently outperforms state-of-the-art models across multiple image restoration benchmarks, achieving dynamic instance-specific recovery with favorable computational scalability. The code is available at https://github.com/Elysiaaaaaaaa/TTTIR.git.
CommentsTL;DR: TTTIR improves image restoration by framing it as an instance-specific state evolution process. Powered by Test-Time Training (TTT), it dynamically adapts operators to handle real-world degradations, outperforming state-of-the-art models with scalable efficiency. 11 pages, 6 figures, 6 tables
