TTTIR: Unlocking Instance-Specific State Evolution via Test-Time Training for Image Restoration

arXiv:2609.26151 · eess.IV, cs.AI, cs.CV, cs.MM · Submitted 2026-09-15 · Read on arXiv

eess.IV, cs.AI, cs.CV, cs.MM

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: TL;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

Code: https://github.com/Elysiaaaaaaaa/TTTIR

License: http://creativecommons.org/licenses/by/4.0/

The gist: Image restoration is inherently challenging due to the diverse and highly input-dependent nature of real-world degradations.

Terminology

Abstract

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.

Sources

Related papers