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

arXiv: https://arxiv.org/abs/2609.26151 · HTML: https://mlsanity.com/paper/2609.26151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 56 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 30 of 39)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [Test-Time Training Done Right](https://mlsanity.com/paper/2505.23884/) (2025)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [One-Minute Video Generation with Test-Time Training](https://mlsanity.com/paper/2504.05298/) (2025)
- [DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention](https://mlsanity.com/paper/2301.04805/) (2023)
- [Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2302.11831/) (2023)
- [MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing](https://mlsanity.com/paper/2308.14036/) (2023)
- [FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information](https://mlsanity.com/paper/2308.03033/) (2023)
- [Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement](https://mlsanity.com/paper/2405.03349/) (2024)
- [Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining](https://mlsanity.com/paper/2404.01547/) (2024)
- [Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2408.01276/) (2024)
- [ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training](https://mlsanity.com/paper/2603.04385/) (2026)
- [MixDehazeNet : Mix Structure Block For Image Dehazing Network](https://mlsanity.com/paper/2305.17654/) (2023)
- [ViT3: Unlocking Test-Time Training in Vision](https://mlsanity.com/paper/2512.01643/) (2025)
- [Magic ELF: Image Deraining Meets Association Learning and Transformer](https://mlsanity.com/paper/2207.10455/) (2022)
- [DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2412.00683/) (2024)
- [LKD-Net: Large Kernel Convolution Network for Single Image Dehazing](https://mlsanity.com/paper/2209.01788/) (2022)
- [tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction](https://mlsanity.com/paper/2602.20160/) (2026)
- [Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training](https://mlsanity.com/paper/2603.12255/) (2026)

## Abstract (arXiv)

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.