# GraftSR: Grafting Authentic Textures for Real-World Image Super-Resolution via Identical-Instance Guidance

arXiv: https://arxiv.org/abs/2608.25334 · HTML: https://mlsanity.com/paper/2608.25334/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 26 Aug 2026.

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

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [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)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Learning Texture Transformer Network for Image Super-Resolution](https://mlsanity.com/paper/2006.04139/) (2020)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [The relativistic discriminator: a key element missing from standard GAN](https://mlsanity.com/paper/1807.00734/) (2018)
- [Diffusion Adversarial Post-Training for One-Step Video Generation](https://mlsanity.com/paper/2501.08316/) (2025)
- [Image Super-Resolution by Neural Texture Transfer](https://mlsanity.com/paper/1903.00834/) (2019)
- [Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach](https://mlsanity.com/paper/2412.03017/) (2024)
- [MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution](https://mlsanity.com/paper/2106.02299/) (2021)
- [Robust Reference-based Super-Resolution via C2-Matching](https://mlsanity.com/paper/2106.01863/) (2021)
- [Reference-based Image Super-Resolution with Deformable Attention Transformer](https://mlsanity.com/paper/2207.11938/) (2022)
- [ReFIR: Grounding Large Restoration Models with Retrieval Augmentation](https://mlsanity.com/paper/2410.05601/) (2024)
- [RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection](https://mlsanity.com/paper/2211.04203/) (2022)
- [Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling](https://mlsanity.com/paper/2602.01864/) (2026)
- [MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration](https://mlsanity.com/paper/2508.16887/) (2025)
- [GarmentZoom: Generating Zoomable Images from Garment Listings](https://mlsanity.com/paper/2606.29535/) (2026)

## Abstract (arXiv)

Diffusion-based real-world image super-resolution (SR) achieves impressive perceptual quality but inherently suffers from severe texture hallucination. To overcome this limitation, we propose GraftSR, a texture-reference-guided generative SR framework that leverages reference images of the identical instance to anchor the restoration of authentic textures. However, severe spatial misalignment between low-quality inputs and their references poses significant challenges, often leading to ambiguous transfer targets and background feature leakage. To address these issues, GraftSR employs a novel dual-mask reference guidance mechanism that systematically decouples the cross-view texture injection process. By explicitly isolating what authentic textures to extract from the reference and precisely localizing where to apply them within the target, GraftSR achieves robust texture transfer without relying on brittle spatial alignment. Furthermore, to bridge the critical gap in appropriate training data, we construct TexRefSR-141K, the first large-scale dataset providing high-quality reference tuples equipped with complementary spatial masks. Extensive experiments on our newly established benchmark, TexRefSR-Eval, demonstrate that GraftSR sets a new state-of-the-art. Notably, it reduces LPIPS by 20.2% over top-performing baselines, achieving superior reference-faithful restoration.