paper-with-me

홈 › Papers

DM$^3$Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matching

2025-06-08 · Cong Guan, Jiacheng Ying, Yuya Ieiri, Osamu Yoshie

Dual-camera super-resolution is highly practical for smartphone photography that primarily super-resolve the wide-angle images using the telephoto image as a reference. In this paper, we propose DM$^3$Net, a novel dual-camera super-resolution network based on Domain Modulation and Multi-scale Matching. To bridge the domain gap between the high-resolution domain and the degraded domain, we learn two compressed global representations from image pairs corresponding to the two domains. To enable reliable transfer of high-frequency structural details from the reference image, we design a multi-scale matching module that conducts patch-level feature matching and retrieval across multiple receptive fields to improve matching accuracy and robustness. Moreover, we also introduce Key Pruning to achieve a significant reduction in memory usage and inference time with little model performance sacrificed. Experimental results on three real-world datasets demonstrate that our DM$^3$Net outperforms the state-of-the-art approaches.

📄 PDF Abstract BibTeX arXiv:2506.06993

Code (0)

등록된 구현이 없습니다.

Tasks

Super-Resolution

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Dual-domain Modulation Network for Lightweight Image Super-Resolution

2025-03-13 · Wenjie Li, Heng Guo, Yuefeng Hou, Guangwei Gao 외

Lightweight image super-resolution (SR) aims to reconstruct high-resolution images from low-resolution images with limited computational costs. We find existing frequency-based SR methods cannot balance the reconstructio…

Image Super-ResolutionSuper-Resolution

Dual-Camera Super-Resolution with Aligned Attention Modules

2021-09-03 · ICCV 2021 10 · Tengfei Wang, Jiaxin Xie, Wenxiu Sun, Qiong Yan 외

We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results. Our proposed meth…

Domain AdaptationReference-based Super-ResolutionSuper-Resolution

Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

2022-07-19 · Xiaoyu Dong, Naoto Yokoya, Longguang Wang, Tatsumi Uezato

Self-supervised cross-modal super-resolution (SR) can overcome the difficulty of acquiring paired training data, but is challenging because only low-resolution (LR) source and high-resolution (HR) guide images from diffe…

Super-Resolution

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

2022-05-07 · CVPR 2022 1 · Xiaoqian Xu, Pengxu Wei, Weikai Chen, Mingzhi Mao 외

Due to the sophisticated imaging process, an identical scene captured by different cameras could exhibit distinct imaging patterns, introducing distinct proficiency among the super-resolution (SR) models trained on image…

Domain AdaptationImage Super-ResolutionSuper-ResolutionUnsupervised Domain Adaptation

Data Acquisition and Preparation for Dual-reference Deep Learning of Image Super-Resolution

2021-08-05 · Yanhui Guo, Xiaolin Wu, Xiao Shu

The performance of deep learning based image super-resolution (SR) methods depend on how accurately the paired low and high resolution images for training characterize the sampling process of real cameras. Low and high r…

Image Super-ResolutionSuper-Resolution