| title | RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement |
|---|---|
| authors | Jeahun Sung, Dahyeon Kye, Soo Ye Kim, Jihyong Oh |
| date | 2026-06-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.15158 |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Reference-guided generation (e.g., object compositing, customization) has progressed rapidly, yet current pipelines share a fundamental limitation: the object-centric high-resolution reference image (HRRI) provided by users is downsampled to a fixed low-resolution (LR) before being fed into the model, so the fine-grained details are discarded before the output is even produced. In addition, the generation step then introduces its own artifacts (e.g., identity distortion) on top of this loss. Existing reference-guided generated content refinement (RefGCR) methods can correct some of these artifacts but still operate in the LR domain; reference-guided super-resolution (RefSR) methods recover resolution but assume natural-image degradations and ignore the artifact distribution of generative pipelines. To address both gaps in a single formulation, we introduce a new task: reference-guided generated content super-resolution-refinement (RefGC-SR^2), where the original HRRI is reused at the post-processing stage to recover lost details, refine generative artifacts, and upscale the output simultaneously. We construct the first real-world triplet data generation pipeline for this RefGC-SR^2 task, training a diptych-conditioned generator to synthesize paired low-quality anchors that public pretrained models cannot provide. We further present a frequency-aware diffusion transformer model for RefGC-SR^2 that selectively injects fine details from the HRRI while removing generative artifacts. Extensive experiments demonstrate that our RefGC-SR^2 model successfully (i) refines the object identity faithfully with respect to the reference, and (ii) recovers high-resolution details, so that the final result is significantly higher quality and practically more usable compared to existing RefGCR and RefSR baselines. |
cite
@misc{sung2026refgc,
title={RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement},
author={Jeahun Sung and Dahyeon Kye and Soo Ye Kim and Jihyong Oh},
year={2026},
eprint={2606.15158},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.15158}
}