Robust Reference-based Super-Resolution via C2-Matching

by   Yuming Jiang, et al.

Reference-based Super-Resolution (Ref-SR) has recently emerged as a promising paradigm to enhance a low-resolution (LR) input image by introducing an additional high-resolution (HR) reference image. Existing Ref-SR methods mostly rely on implicit correspondence matching to borrow HR textures from reference images to compensate for the information loss in input images. However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e.g. scale and rotation) and the resolution gap (e.g. HR and LR). To tackle these challenges, we propose C2-Matching in this work, which produces explicit robust matching crossing transformation and resolution. 1) For the transformation gap, we propose a contrastive correspondence network, which learns transformation-robust correspondences using augmented views of the input image. 2) For the resolution gap, we adopt a teacher-student correlation distillation, which distills knowledge from the easier HR-HR matching to guide the more ambiguous LR-HR matching. 3) Finally, we design a dynamic aggregation module to address the potential misalignment issue. In addition, to faithfully evaluate the performance of Ref-SR under a realistic setting, we contribute the Webly-Referenced SR (WR-SR) dataset, mimicking the practical usage scenario. Extensive experiments demonstrate that our proposed C2-Matching significantly outperforms state of the arts by over 1dB on the standard CUFED5 benchmark. Notably, it also shows great generalizability on WR-SR dataset as well as robustness across large scale and rotation transformations.


page 1

page 5

page 7

page 8

page 13

page 14

page 15


Reference-based Image and Video Super-Resolution via C2-Matching

Reference-based Super-Resolution (Ref-SR) has recently emerged as a prom...

Towards Compact Single Image Super-Resolution via Contrastive Self-distillation

Convolutional neural networks (CNNs) are highly successful for super-res...

Texture Hallucination for Large-Scale Painting Super-Resolution

We aim to super-resolve digital paintings, synthesizing realistic detail...

Reference-based Image Super-Resolution with Deformable Attention Transformer

Reference-based image super-resolution (RefSR) aims to exploit auxiliary...

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution

Reference-based image super-resolution (RefSR) has shown promising succe...

Unsupervised Remote Sensing Super-Resolution via Migration Image Prior

Recently, satellites with high temporal resolution have fostered wide at...

RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution

Smartphones equipped with a multi-camera system comprising multiple came...

Please sign up or login with your details

Forgot password? Click here to reset