# Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models

arXiv: https://arxiv.org/abs/2503.11073 · HTML: https://mlsanity.com/paper/2503.11073/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 42 of its 58 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 30 of 42)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)

## Built on by (most cited first, 24 of 24)

- [Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model](https://mlsanity.com/paper/2509.04548/) (2025)
- [Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training](https://mlsanity.com/paper/2507.20291/) (2025)
- [Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy](https://mlsanity.com/paper/2510.09012/) (2025)
- [VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction](https://mlsanity.com/paper/2511.23386/) (2025)
- [MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition](https://mlsanity.com/paper/2512.07348/) (2025)
- [UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis](https://mlsanity.com/paper/2507.00992/) (2025)
- [Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling](https://mlsanity.com/paper/2601.15664/) (2026)
- [RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought](https://mlsanity.com/paper/2506.16796/) (2025)
- [Text-guided Visual Prompt DINO for Generic Segmentation](https://mlsanity.com/paper/2508.06146/) (2025)
- [UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement](https://mlsanity.com/paper/2512.06750/) (2025)
- [Universal Image Restoration Pre-training via Masked Degradation Classification](https://mlsanity.com/paper/2510.13282/) (2025)
- [FAPE-IR: Frequency-Aware Planning and Execution Framework for All-in-One Image Restoration](https://mlsanity.com/paper/2511.14099/) (2025)
- [TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration](https://mlsanity.com/paper/2601.20306/) (2026)
- [Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration](https://mlsanity.com/paper/2601.19506/) (2026)
- [OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution](https://mlsanity.com/paper/2603.12811/) (2026)
- [GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration](https://mlsanity.com/paper/2605.31039/) (2026)
- [Bridging Degradation Discrimination and Generation for Universal Image Restoration](https://mlsanity.com/paper/2602.00579/) (2026)
- [AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution](https://mlsanity.com/paper/2603.00589/) (2026)
- [UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints](https://mlsanity.com/paper/2603.10517/) (2026)
- [TextOVSR: Text-Guided Real-World Opera Video Super-Resolution](https://mlsanity.com/paper/2603.15153/) (2026)
- [Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement](https://mlsanity.com/paper/2604.16858/) (2026)
- [Hierarchical Image Tokenization for Multi-Scale Image Super Resolution](https://mlsanity.com/paper/2605.14891/) (2026)
- [Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution](https://mlsanity.com/paper/2607.17612/) (2026)
- [GeoMAR: Unleashing Geometrically Aligned Features for Masked Autoregressive Blind Face Restoration](https://mlsanity.com/paper/2608.03923/) (2026)

## Abstract (arXiv)

By leveraging the generative priors from pre-trained text-to-image diffusion models, significant progress has been made in real-world image super-resolution (Real-ISR). However, these methods tend to generate inaccurate and unnatural reconstructions in complex and/or heavily degraded scenes, primarily due to their limited perception and understanding capability of the input low-quality image. To address these limitations, we propose, for the first time to our knowledge, to adapt the pre-trained autoregressive multimodal model such as Lumina-mGPT into a robust Real-ISR model, namely PURE, which Perceives and Understands the input low-quality image, then REstores its high-quality counterpart. Specifically, we implement instruction tuning on Lumina-mGPT to perceive the image degradation level and the relationships between previously generated image tokens and the next token, understand the image content by generating image semantic descriptions, and consequently restore the image by generating high-quality image tokens autoregressively with the collected information. In addition, we reveal that the image token entropy reflects the image structure and present a entropy-based Top-k sampling strategy to optimize the local structure of the image during inference. Experimental results demonstrate that PURE preserves image content while generating realistic details, especially in complex scenes with multiple objects, showcasing the potential of autoregressive multimodal generative models for robust Real-ISR. The model and code will be available at https://github.com/nonwhy/PURE.