English
Related papers

Related papers: RAW-Domain Degradation Models for Realistic Smartp…

200 papers

The state of the art in video super-resolution (SR) are techniques based on deep learning, but they perform poorly on real-world videos (see Figure 1). The reason is that training image-pairs are commonly created by downscaling a…

Computer Vision and Pattern Recognition · Computer Science 2021-05-07 Noam Elron , Alex Itskovich , Shahar S. Yuval , Noam Levy

We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught…

Image and Video Processing · Electrical Eng. & Systems 2026-02-03 Yan Chen , Yi Wen , Wei Li , Junchao Liu , Yong Guo , Jie Hu , Xinghao Chen

Recently, reference-based image super-resolution (RefSR) has shown excellent performance in image super-resolution (SR) tasks. The main idea of RefSR is to utilize additional information from the reference (Ref) image to recover the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Jeongho Min , Yejun Lee , Dongyoung Kim , Jaejun Yoo

Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degrada-tion process from that in the real-world scenario. Conventional degradation processes consider…

Image and Video Processing · Electrical Eng. & Systems 2022-02-14 Zhenxing Dong , Hong Cao , Wang Shen , Yu Gan , Yuye Ling , Guangtao Zhai , Yikai Su

Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data…

Image and Video Processing · Electrical Eng. & Systems 2023-05-05 Mehran Jeelani , Sadbhawna , Noshaba Cheema , Klaus Illgner-Fehns , Philipp Slusallek , Sunil Jaiswal

Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels. However, real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the…

Image and Video Processing · Electrical Eng. & Systems 2024-07-11 Yuehan Zhang , Seungjun Lee , Angela Yao

These days, unsupervised super-resolution (SR) has been soaring due to its practical and promising potential in real scenarios. The philosophy of off-the-shelf approaches lies in the augmentation of unpaired data, i.e. first generating…

Computer Vision and Pattern Recognition · Computer Science 2020-04-03 Yunxuan Wei , Shuhang Gu , Yawei Li , Longcun Jin

Deep Convolution Neural Networks (CNN) have achieved significant performance on single image super-resolution (SR) recently. However, existing CNN-based methods use artificially synthetic low-resolution (LR) and high-resolution (HR) image…

Computer Vision and Pattern Recognition · Computer Science 2018-12-14 Tianyu Zhao , Wenqi Ren , Changqing Zhang , Dongwei Ren , Qinghua Hu

Image signal processing (ISP) pipeline plays a fundamental role in digital cameras, which converts raw Bayer sensor data to RGB images. However, ISP-generated images usually suffer from imperfections due to the compounded degradations that…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Yanhui Guo , Fangzhou Luo , Xiaolin Wu

Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data.…

Image and Video Processing · Electrical Eng. & Systems 2024-04-30 Brian B. Moser , Ahmed Anwar , Federico Raue , Stanislav Frolov , Andreas Dengel

Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Jianrui Cai , Hui Zeng , Hongwei Yong , Zisheng Cao , Lei Zhang

This paper shows that when applying machine learning to digital zoom for photography, it is beneficial to use real, RAW sensor data for training. Existing learning-based super-resolution methods do not use real sensor data, instead…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Xuaner Cecilia Zhang , Qifeng Chen , Ren Ng , Vladlen Koltun

Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling). However, these methods suffer a severe performance drop when the real…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Longguang Wang , Yingqian Wang , Xiaoyu Dong , Qingyu Xu , Jungang Yang , Wei An , Yulan Guo

Physical photographs now can be conveniently scanned by smartphones and stored forever as a digital version, yet the scanned photos are not restored well. One solution is to train a supervised deep neural network on many digital photos and…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Man M. Ho , Jinjia Zhou

Depth maps captured with commodity sensors are often of low quality and resolution; these maps need to be enhanced to be used in many applications. State-of-the-art data-driven methods of depth map super-resolution rely on registered pairs…

Computer Vision and Pattern Recognition · Computer Science 2022-09-26 Aleksandr Safin , Maxim Kan , Nikita Drobyshev , Oleg Voynov , Alexey Artemov , Alexander Filippov , Denis Zorin , Evgeny Burnaev

In this paper, we consider two challenging issues in reference-based super-resolution (RefSR) for smartphone, (i) how to choose a proper reference image, and (ii) how to learn RefSR in a self-supervised manner. Particularly, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Zhilu Zhang , Ruohao Wang , Hongzhi Zhang , Wangmeng Zuo

Most image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs that are constructed by a predetermined operation, e.g., bicubic downsampling. As existing methods typically learn…

Image and Video Processing · Electrical Eng. & Systems 2021-09-09 Sanghyun Son , Jaeha Kim , Wei-Sheng Lai , Ming-Husan Yang , Kyoung Mu Lee

Traditional face super-resolution (FSR) methods trained on synthetic datasets usually have poor generalization ability for real-world face images. Recent work has utilized complex degradation models or training networks to simulate the real…

Image and Video Processing · Electrical Eng. & Systems 2024-05-09 Zhilei Liu , Chenggong Zhang

Despite achieving remarkable progress in recent years, single-image super-resolution methods are developed with several limitations. Specifically, they are trained on fixed content domains with certain degradations (whether synthetic or…

Computer Vision and Pattern Recognition · Computer Science 2022-08-29 Xiaoyu Lin , Baran Ozaydin , Vidit Vidit , Majed El Helou , Sabine Süsstrunk

In this paper, we examine the problem of real-world image deblurring and take into account two key factors for improving the performance of the deep image deblurring model, namely, training data synthesis and network architecture design.…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Hao Wei , Chenyang Ge , Xin Qiao , Pengchao Deng