Fidelity-Naturalness Evaluation of Single Image Super Resolution
We study the problem of evaluating super resolution methods. Traditional evaluation methods usually judge the quality of super resolved images based on a single measure of their difference with the original high resolution images. In this paper, we proposed to use both fidelity (the difference with original images) and naturalness (human visual perception of super resolved images) for evaluation. For fidelity evaluation, a new metric is proposed to solve the bias problem of traditional evaluation. For naturalness evaluation, we let humans label preference of super resolution results using pair-wise comparison, and test the correlation between human labeling results and image quality assessment metrics' outputs. Experimental results show that our fidelity-naturalness method is better than the traditional evaluation method for super resolution methods, which could help future research on single-image super resolution.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Quality AssessmentImage Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness
Single image super-resolution (SISR) algorithms reconstruct high-resolution (HR) images with their low-resolution (LR) counterparts. It is desirable to develop image quality assessment (IQA) methods that can not only eva…
Generative Adversarial NetworkImage Quality AssessmentImage Super-ResolutionSuper-ResolutionIs Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation
Text-to-speech (TTS) evaluation is an open challenge. While the primary target was "naturalness," recent fidelity gains shifted focus toward "appropriateness" and whether speech is correct for its context. In this work, …
Spatio-Temporal Perception-Distortion Trade-off in Learned Video SR
Perception-distortion trade-off is well-understood for single-image super-resolution. However, its extension to video super-resolution (VSR) is not straightforward, since popular perceptual measures only evaluate natural…
Image Super-ResolutionOptical Flow EstimationSuper-ResolutionVideo Super-ResolutionNatural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discrimination
Recently, many convolutional neural networks for single image super-resolution (SISR) have been proposed, which focus on reconstructing the high-resolution images in terms of objective distortion measures. However, the n…
Image Super-ResolutionSuper-ResolutionBigGAN-based Bayesian reconstruction of natural images from human brain activity
In the visual decoding domain, visually reconstructing presented images given the corresponding human brain activity monitored by functional magnetic resonance imaging (fMRI) is difficult, especially when reconstructing …
Conditional Image GenerationGenerative Adversarial NetworkImage Generation