Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling

About

Recent works have explored reference-based super-resolution (RefSR) to mitigate hallucinations in diffusion-based image restoration. A key challenge is that real-world degradations make correspondences between low-quality (LQ) inputs and reference (Ref) images unreliable, requiring adaptive control of reference usage. Existing methods either ignore LQ-Ref correlations or rely on brittle explicit matching, leading to over-reliance on misleading references or under-utilization of valuable cues. To address this, we propose Ada-RefSR, a single-step diffusion framework guided by a "Trust but Verify" principle: reference information is leveraged when reliable and suppressed otherwise. Its core component, Adaptive Implicit Correlation Gating (AICG), employs learnable summary tokens to distill dominant reference patterns and capture implicit correlations with LQ features. Integrated into the attention backbone, AICG provides lightweight, adaptive regulation of reference guidance, serving as a built-in safeguard against erroneous fusion. Experiments on multiple datasets demonstrate that Ada-RefSR achieves a strong balance of fidelity, naturalness, and efficiency, while remaining robust under varying reference alignment.

Yuan Wang, Yuhao Wan, Siming Zheng, Bo Li, Qibin Hou, Peng-Tao Jiang• 2026

Related benchmarks

TaskDatasetResultRank
Image Super-resolutionFace
PSNR27.1271
11
Image Super-resolutionCUFED5
PSNR20.4843
9
Image Super-resolutionWRSR
PSNR21.9722
9
Reference-based Super-ResolutionGarment dataset 10x
LPIPS0.29
8
Reference-based Super-ResolutionGarment dataset 4x
LPIPS0.222
8
Image Super-resolutionBird
PSNR25.2998
7
Reference-guided Image Super-ResolutionIn-the-wild Compositing
CLIP-I0.829
7
Reference-guided Image Super-ResolutionIn-the-wild Customization
CLIP-I0.7206
7
Reference Super-Resolution (RefSR)RefGC-SR²
CLIP-I Score0.8311
4
Showing 9 of 9 rows

Other info

Follow for update