SRFlow: Learning the Super-Resolution Space with Normalizing Flow
- URL: http://arxiv.org/abs/2006.14200v2
- Date: Fri, 31 Jul 2020 14:55:35 GMT
- Title: SRFlow: Learning the Super-Resolution Space with Normalizing Flow
- Authors: Andreas Lugmayr and Martin Danelljan and Luc Van Gool and Radu Timofte
- Abstract summary: Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image.
We propose SRFlow: a normalizing flow based super-resolution method capable of learning the conditional distribution of the output.
Our model is trained in a principled manner using a single loss, namely the negative log-likelihood.
- Score: 176.07982398988747
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Super-resolution is an ill-posed problem, since it allows for multiple
predictions for a given low-resolution image. This fundamental fact is largely
ignored by state-of-the-art deep learning based approaches. These methods
instead train a deterministic mapping using combinations of reconstruction and
adversarial losses. In this work, we therefore propose SRFlow: a normalizing
flow based super-resolution method capable of learning the conditional
distribution of the output given the low-resolution input. Our model is trained
in a principled manner using a single loss, namely the negative log-likelihood.
SRFlow therefore directly accounts for the ill-posed nature of the problem, and
learns to predict diverse photo-realistic high-resolution images. Moreover, we
utilize the strong image posterior learned by SRFlow to design flexible image
manipulation techniques, capable of enhancing super-resolved images by, e.g.,
transferring content from other images. We perform extensive experiments on
faces, as well as on super-resolution in general. SRFlow outperforms
state-of-the-art GAN-based approaches in terms of both PSNR and perceptual
quality metrics, while allowing for diversity through the exploration of the
space of super-resolved solutions.
Related papers
- Boosting Flow-based Generative Super-Resolution Models via Learned Prior [8.557017814978334]
Flow-based super-resolution (SR) models have demonstrated astonishing capabilities in generating high-quality images.
These methods encounter several challenges during image generation, such as grid artifacts, exploding inverses, and suboptimal results due to a fixed sampling temperature.
This work introduces a conditional learned prior to the inference phase of a flow-based SR model.
arXiv Detail & Related papers (2024-03-16T18:04:12Z) - Local Implicit Normalizing Flow for Arbitrary-Scale Image
Super-Resolution [11.653044501483667]
We propose "Local Implicit Normalizing Flow" (LINF) as a unified solution to the above problems.
LINF models the distribution of texture details under different scaling factors with normalizing flow.
We show that LINF achieves the state-of-the-art perceptual quality compared with prior arbitrary-scale SR methods.
arXiv Detail & Related papers (2023-03-09T10:20:07Z) - Blind Super-Resolution for Remote Sensing Images via Conditional
Stochastic Normalizing Flows [14.882417028542855]
We propose a novel blind SR framework based on the normalizing flow (BlindSRSNF) to address the above problems.
BlindSRSNF learns the conditional probability distribution over the high-resolution image space given a low-resolution (LR) image by explicitly optimizing the variational bound on the likelihood.
We show that the proposed algorithm can obtain SR results with excellent visual perception quality on both simulated LR and real-world RSIs.
arXiv Detail & Related papers (2022-10-14T12:37:32Z) - Hierarchical Similarity Learning for Aliasing Suppression Image
Super-Resolution [64.15915577164894]
A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing.
HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
arXiv Detail & Related papers (2022-06-07T14:55:32Z) - Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic
Super-resolution [161.39504409401354]
Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions.
Yet, the dominant paradigm is to employ pixel-wise losses, such as L_, which drive the prediction towards a blurry average.
We address this issue by revisiting the L_ loss and show that it corresponds to a one-layer conditional flow.
Inspired by this relation, we explore general flows as a fidelity-based alternative to the L_ objective.
We demonstrate that the flexibility of deeper flows leads to better visual quality and consistency when combined with adversarial losses.
arXiv Detail & Related papers (2021-11-05T17:56:51Z) - Hierarchical Conditional Flow: A Unified Framework for Image
Super-Resolution and Image Rescaling [139.25215100378284]
We propose a hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling.
HCFlow learns a mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously.
To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training.
arXiv Detail & Related papers (2021-08-11T16:11:01Z) - SRWarp: Generalized Image Super-Resolution under Arbitrary
Transformation [65.88321755969677]
Deep CNNs have achieved significant successes in image processing and its applications, including single image super-resolution.
Recent approaches extend the scope to real-valued upsampling factors.
We propose the SRWarp framework to further generalize the SR tasks toward an arbitrary image transformation.
arXiv Detail & Related papers (2021-04-21T02:50:41Z) - PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of
Generative Models [77.32079593577821]
PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature.
Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
arXiv Detail & Related papers (2020-03-08T16:44:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.