Generalized Real-World Super-Resolution through Adversarial Robustness
- URL: http://arxiv.org/abs/2108.11505v1
- Date: Wed, 25 Aug 2021 22:43:20 GMT
- Title: Generalized Real-World Super-Resolution through Adversarial Robustness
- Authors: Angela Castillo, Mar\'ia Escobar, Juan C. P\'erez, Andr\'es Romero,
Radu Timofte, Luc Van Gool and Pablo Arbel\'aez
- Abstract summary: We present Robust Super-Resolution, a method that leverages the generalization capability of adversarial attacks to tackle real-world SR.
Our novel framework poses a paradigm shift in the development of real-world SR methods.
By using a single robust model, we outperform state-of-the-art specialized methods on real-world benchmarks.
- Score: 107.02188934602802
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Real-world Super-Resolution (SR) has been traditionally tackled by first
learning a specific degradation model that resembles the noise and corruption
artifacts in low-resolution imagery. Thus, current methods lack generalization
and lose their accuracy when tested on unseen types of corruption. In contrast
to the traditional proposal, we present Robust Super-Resolution (RSR), a method
that leverages the generalization capability of adversarial attacks to tackle
real-world SR. Our novel framework poses a paradigm shift in the development of
real-world SR methods. Instead of learning a dataset-specific degradation, we
employ adversarial attacks to create difficult examples that target the model's
weaknesses. Afterward, we use these adversarial examples during training to
improve our model's capacity to process noisy inputs. We perform extensive
experimentation on synthetic and real-world images and empirically demonstrate
that our RSR method generalizes well across datasets without re-training for
specific noise priors. By using a single robust model, we outperform
state-of-the-art specialized methods on real-world benchmarks.
Related papers
- Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution [38.79439380482431]
Real-world super-resolution (RWSR) faces unknown degradations in the low-resolution inputs, all the while lacking paired training data.
Existing methods approach this problem by learning blind general models through complex synthetic augmentations on training inputs.
We introduce a novel pairwise distance distillation framework to address the unsupervised RWSR for a targeted real-world degradation.
arXiv Detail & Related papers (2024-07-10T01:46:40Z) - Towards Realistic Data Generation for Real-World Super-Resolution [79.24617577528593]
RealDGen is an unsupervised learning data generation framework designed for real-world super-resolution.
We develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model.
Experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations.
arXiv Detail & Related papers (2024-06-11T13:34:57Z) - Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution [7.638042073679073]
This paper explores the universality of various methods for enhancing the robustness of deep learning Super-Resolution models.
We show that median randomized smoothing (MRS) is more general in terms of robustness compared to adversarial learning techniques.
As expected, we also illustrate that the proposed universal robust method enables the SR model to handle standard corruptions more effectively.
arXiv Detail & Related papers (2024-05-23T18:00:01Z) - Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable
Image Super Resolution [46.31021254956368]
We argue that Dropout simultaneously introduces undesirable side-effect that compromises model's capacity to faithfully reconstruct fine details.
We present another easy yet effective training strategy that enhances the generalization ability of the model by simply modulating its first and second-order features statistics.
Experimental results have shown that our method could serve as a model-agnostic regularization and outperforms Dropout on seven benchmark datasets.
arXiv Detail & Related papers (2024-02-29T07:44:31Z) - Crafting Training Degradation Distribution for the
Accuracy-Generalization Trade-off in Real-World Super-Resolution [53.0437282872811]
We introduce a novel approach to craft training degradation distributions using a small set of reference images.
Our results indicate that the proposed technique significantly improves the performance of test images while preserving generalization capabilities in real-world applications.
arXiv Detail & Related papers (2023-05-29T14:22:48Z) - Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution.
By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
arXiv Detail & Related papers (2023-05-11T17:55:25Z) - Toward Real-World Super-Resolution via Adaptive Downsampling Models [58.38683820192415]
This study proposes a novel method to simulate an unknown downsampling process without imposing restrictive prior knowledge.
We propose a generalizable low-frequency loss (LFL) in the adversarial training framework to imitate the distribution of target LR images without using any paired examples.
arXiv Detail & Related papers (2021-09-08T06:00:32Z) - Best-Buddy GANs for Highly Detailed Image Super-Resolution [71.13466303340192]
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input.
Most methods along this line rely on a predefined single-LR-single-HR mapping, which is not flexible enough for the SISR task.
We propose best-buddy GANs (Beby-GAN) for rich-detail SISR. Relaxing the immutable one-to-one constraint, we allow the estimated patches to dynamically seek the best supervision.
arXiv Detail & Related papers (2021-03-29T02:58:27Z)
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.