Single Image Super Resolution - When Model Adaptation Matters
In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external priors modeling are the key ingredients. The internal contents of the low resolution input image is neglected with deep modeling despite the earlier works showing the power of using such internal priors. In this paper we propose a novel deep convolutional neural network carefully designed for robustness and efficiency at both learning and testing. Moreover, we propose a couple of model adaptation strategies to the internal contents of the low resolution input image and analyze their strong points and weaknesses. By trading runtime and using internal priors we achieve 0.1 up to 0.3dB PSNR improvements over best reported results on standard datasets. Our adaptation especially favors images with repetitive structures or under large resolutions. Moreover, it can be combined with other simple techniques, such as back-projection or enhanced prediction, for further improvements.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Image-to-image domain adaptation for vehicle re-identification
Cross-domain vehicle re-identification (ReID) is an interesting but challenging task in computer vision. A ReID model well-trained on one dataset often experiences a severe performance drop when applied to another datase…
Domain AdaptationGenerative Adversarial NetworkImage Super-ResolutionSuper-Resolution+2Sub-Aperture Feature Adaptation in Single Image Super-resolution Model for Light Field Imaging
With the availability of commercial Light Field (LF) cameras, LF imaging has emerged as an up and coming technology in computational photography. However, the spatial resolution is significantly constrained in commercial…
Image Super-ResolutionSuper-ResolutionMeta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated un…
Blind Super-ResolutionImage Super-ResolutionSuper-ResolutionMeta-Transfer Learning for Zero-Shot Super-Resolution
Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, the…
Image Super-ResolutionMeta-LearningSuper-ResolutionTransfer LearningAdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution
Recovering high-frequency details and textures from low-resolution images remains a fundamental challenge in super-resolution (SR), especially when real-world degradations are complex and unknown. While GAN-based methods…
GPUSuper-Resolution