Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g., image restoration). In this paper, we provide a comprehensive analysis of the existing augmentation methods applied to the super-resolution task. We find that the methods discarding or manipulating the pixels or features too much hamper the image restoration, where the spatial relationship is very important. Based on our analyses, we propose CutBlur that cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. The key intuition of CutBlur is to enable a model to learn not only "how" but also "where" to super-resolve an image. By doing so, the model can understand "how much", instead of blindly learning to apply super-resolution to every given pixel. Our method consistently and significantly improves the performance across various scenarios, especially when the model size is big and the data is collected under real-world environments. We also show that our method improves other low-level vision tasks, such as denoising and compression artifact removal.
Code (2)
Tasks
Data AugmentationDenoisingImage RestorationImage Super-ResolutionSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation
Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated image is always treated as either positi…
Contrastive LearningData AugmentationWhat Are We Really Measuring? Rethinking Dataset Bias in Web-Scale Natural Image Collections via Unsupervised Semantic Clustering
In computer vision, a prevailing method for quantifying dataset bias is to train a model to distinguish between datasets. High classification accuracy is then interpreted as evidence of meaningful semantic differences. T…
Semantic SimilaritySwiftSRGAN -- Rethinking Super-Resolution for Efficient and Real-time Inference
In recent years, there have been several advancements in the task of image super-resolution using the state of the art Deep Learning-based architectures. Many super-resolution-based techniques previously published, requi…
Image Super-ResolutionSuper-ResolutionCascaded Diffusion Models for High Fidelity Image Generation
We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample qualit…
Data AugmentationImage GenerationSuper-ResolutionVocal Bursts Intensity PredictionRGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
We present RGB-D-Fusion, a multi-modal conditional denoising diffusion probabilistic model to generate high resolution depth maps from low-resolution monocular RGB images of humanoid subjects. RGB-D-Fusion first generate…
DenoisingSuper-Resolution