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

Qifan Yu; Haoran Bai; Zongyao He; Weijie He; Sibin Deng; Honggang Qi; Ying Chen

cs.CVAug 26, 2026

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

Authors: Qifan Yu, Haoran Bai, Zongyao He, Weijie He, Sibin Deng, Honggang Qi, Ying Chen

Organizations: Taobao & Tmall Group of Alibaba · University of Chinese Academy of Sciences

Abstract

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.

Figures & tables

Figure 1: GraftSR achieves reference-faithful image SR of fine-grained details ( e.g. , material textures and delicate prints), whereas existing methods exhibit distinct limitations: (a) Diffusion-based SR generates hallucinated textures ; (b) Reference-based SR introduces artifacts beyond matched regions ; and (c) Generative editing model suffers from poor content fidelity .

Figure 2: Overview architecture of GraftSR. Driven by a dual-mask reference guidance mechanism, it extracts mask-modulated reference tokens and region-aware semantic tokens to condition the MMDiT blocks for one-step reference-faithful restoration.

Figure 3: The proposed VLM-driven data curation pipeline. It retrieves identical-instance triplets from multi-view galleries and extracts the complementary masks and unified caption to support authentic texture transfer.

Figure 4: Dataset statistics. (a) Reference distribution over the top-15 leaf categories, with long-tail categories merged as "Others". (b) Number of HQ images per category (bars) and the average number of HQ images per reference (line).

Type	Method	Full-Reference				No-Reference
Type	Method	LPIPS $\downarrow$	DISTS $\downarrow$	PSNR $\uparrow$	SSIM $\uparrow$	MUSIQ $\uparrow$	NIQE $\downarrow$	CLIPIQA $\uparrow$	MANIQA $\uparrow$
Open-source Generative SR	OSEDiff	0.2326	0.1444	28.3752	0.8471	65.2201	4.8256	0.6631	0.5250
	SUPIR	0.2208	0.1321	29.3151	0.8382	61.5577	5.2317	0.5922	0.5225
	DiT4SR	0.3816	0.2147	25.6121	0.8071	33.1845	7.3649	0.5769	0.4253
	ODTSR	0.1983	0.1048	29.5098	0.8431	69.2601	4.7789	0.6176	0.5129
	PiSA-SR	0.2247	0.1343	28.5478	0.8458	66.7754	4.6765	0.6831	0.5338

Table 1: Quantitative comparison on the TexRefSR-Eval-Syn benchmark, where ground-truth references are available. Both full-reference and no-reference metrics are reported. Red bold and blue underline denote the best and the second-best results.

Type	Method	No-Reference				VLM Evaluation (GPT-4.1-global)
Type	Method	NIQE $\downarrow$	MUSIQ $\uparrow$	CLIPIQA $\uparrow$	MANIQA $\uparrow$	PQ $\uparrow$	TC $\uparrow$	Overall $\uparrow$
Open-source Generative SR	OSEDiff	3.9329	70.5668	0.6395	0.6292	3.320	1.740	2.530
	SUPIR	4.2105	59.6691	0.4778	0.5741	3.380	1.960	2.670
	DiT4SR	3.7190	72.5782	0.6428	0.6485	3.720	2.040	2.880
	ODTSR	4.2809	71.5261	0.6140	0.6580	2.760	1.560	2.160
	PiSA-SR	4.2523	65.5855	0.4913	0.5789	2.840	1.660	2.250

Table 2: Quantitative comparison on the TexRefSR-Eval-Real benchmark with no-reference metrics and VLM-based metrics.

Figure 5: Qualitative comparison on TexRefSR-Eval, including one synthetic case with GT (top) and two real cases (bottom). Our method achieves reference-faithful restoration with superior fidelity and texture consistency. ( Zoom in for best view )

Dataset	Method	PSNR $\uparrow$	SSIM $\uparrow$	LPIPS $\downarrow$	MUSIQ $\uparrow$	MANIQA $\uparrow$
RealSR	SUPIR	23.65	0.6620	0.3541	62.09	0.5780
	DiT4SR	23.50	0.6657	0.3215	67.76	0.6564
	OSEDiff	25.15	0.7341	0.2920	69.08	0.6335
	PiSA-SR	25.40	0.7418	0.2672	70.14	0.6551
	VOSR-1.4B	25.23	0.7175	0.2732	70.58	0.6443
	ODTSR	25.07	0.7361	0.2398	68.29	0.6622

Table 3: Quantitative comparison on geneal real-world SR. our GraftSR still achieves strong generalization in both fidelity and perceptual quality even without reference images.

Figure 6: Robustness analysis of GraftSR with absent or mismatched references during inference.

Figure 7: Visual comparison of the ablation studies.

Variant	NIQE $\downarrow$	MUSIQ $\uparrow$	CLIPIQA $\uparrow$	MANIQA $\uparrow$	PQ $\uparrow$	TC $\uparrow$
Ablation on Texture Reference Injection
Cross-attn	4.2210	70.55	0.5236	0.5874	2.660	1.840
Cross-attn + Dual-Mask	3.9818	71.83	0.5974	0.6168	3.000	2.000
Joint-attn	4.4200	71.07	0.5835	0.6278	3.400	2.100
Ablation on Dual-Mask Reference Guidance
w/o $z_{\text{ref}}$	4.2911	72.60	0.6222	0.6469	3.500	2.220

Table 4: Ablation studies on the texture reference injection strategy and the dual-mask reference guidance module.

Figure 8: The user study results. Our method is consistently preferred over SOTA ODTSR and Gemini-3-Pro.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 2: More qualitative comparisons on the TexRefSR-Eval-Syn dataset, where low-quality inputs are produced by the synthetic degradation model. Guided by the reference, our method restores textures that are more faithful to the ground truth, recovering fine patterns and structural details that other methods either over-smooth or hallucinate incorrectly.

Figure 3: More qualitative comparisons on the TexRefSR-Eval-Real dataset, which contains real-world low-quality images without ground truth. Our method produces perceptually sharper results whose textures remain consistent with the reference, whereas other methods tend to yield blurry or unfaithful reconstructions.

Figure 4: More qualitative comparisons on general real-world SR benchmarks (RealSR and DRealSR). Although no reference is available in this setting, our method still generalizes well to natural scenes and recovers clean, realistic details that are competitive with or superior to state-of-the-art general SR methods.

Reference-Based Image Super-Resolution

See all 10 papers

GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution
Apr 28, 2026Fabio D'Oronzio, Federico Putamorsi, Leonardo Zini +2Diffusion Models for Image Restoration Diffusion Model Fine-Tuning
University of Modena and Reggio Emilia, Italy
Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution
May 18, 2026Bin Luo, Runmin Dong, Zhaoyang Luo +4Diffusion Models for Image Restoration Diffusion Transformer
Tsinghua Shenzhen International Graduate School, Shenzhen, China · Sun Yat-sen University, Zhuhai, China · Tsinghua University, Beijing, China +1
Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution
Sep 27, 2026Xingfu Yi, Xiaoxue YuDiffusion Models for Image Restoration Diffusion Transformer
Independent Researcher, Hangzhou, China · Zhejiang University, Hangzhou, China

Apr 28, 2026J/K move · Enter open · S save

GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution

Fabio D'Oronzio, Federico Putamorsi, Leonardo Zini, Marcella Cornia+1

University of Modena and Reggio Emilia, Italy

Diffusion Models for Image Restoration Diffusion Model Fine-Tuning Conditional Diffusion Models Image Super-Resolution

Open paper AskPDF arXiv

Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong generative priors but commonly rely on text conditioning derived from semantic captioning. Such textual descriptions provide only high-level semantics and lack the spatially aligned visual information required for faithful restoration, leading to a representation gap between abstract semantics and spatially aligned visual details. To address this limitation, we propose GramSR, a one-step diffusion-based SR framework that replaces text conditioning with dense visual features extracted from the low-resolution input using a pre-trained DINOv3 encoder. GramSR adopts a three-stage LoRA architecture, where pixel-level, semantic-level, and texture-level LoRA modules are trained sequentially. The pixel-level module focuses on degradation removal using

\ell_2

loss, the semantic-level module enhances perceptual details via LPIPS and CSD losses, and the texture-level module enforces feature correlation consistency through a Gram matrix loss computed from DINOv3 features. At inference, independent guidance scales enable flexible control over degradation removal, semantic enhancement, and texture preservation. Extensive experiments on standard SR benchmarks demonstrate that GramSR consistently outperforms existing one-step diffusion-based methods, achieving superior structural fidelity and texture realism. The code for this work is available at: https://github.com/aimagelab/GramSR.

Abstract

Reference-Based Image Super-Resolution

Explore similar work

GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution

Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution

Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution