Towards True Detail Restoration for Super-Resolution: A Benchmark and a
Quality Metric
- URL: http://arxiv.org/abs/2203.08923v1
- Date: Wed, 16 Mar 2022 20:13:35 GMT
- Title: Towards True Detail Restoration for Super-Resolution: A Benchmark and a
Quality Metric
- Authors: Eugene Lyapustin, Anastasia Kirillova, Viacheslav Meshchaninov,
Evgeney Zimin, Nikolai Karetin, Dmitriy Vatolin
- Abstract summary: Super-resolution (SR) methods can improve overall image and video quality and create new possibilities for content analysis.
But the SR mainstream focuses primarily on increasing the naturalness of the resulting image.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Super-resolution (SR) has become a widely researched topic in recent years.
SR methods can improve overall image and video quality and create new
possibilities for further content analysis. But the SR mainstream focuses
primarily on increasing the naturalness of the resulting image despite
potentially losing context accuracy. Such methods may produce an incorrect
digit, character, face, or other structural object even though they otherwise
yield good visual quality. Incorrect detail restoration can cause errors when
detecting and identifying objects both manually and automatically. To analyze
the detail-restoration capabilities of image and video SR models, we developed
a benchmark based on our own video dataset, which contains complex patterns
that SR models generally fail to correctly restore. We assessed 32 recent SR
models using our benchmark and compared their ability to preserve scene
context. We also conducted a crowd-sourced comparison of restored details and
developed an objective assessment metric that outperforms other quality metrics
by correlation with subjective scores for this task. In conclusion, we provide
a deep analysis of benchmark results that yields insights for future SR-based
work.
Related papers
- Perception- and Fidelity-aware Reduced-Reference Super-Resolution Image Quality Assessment [25.88845910499606]
We propose a novel dual-branch reduced-reference SR-IQA network, ie, Perception- and Fidelity-aware SR-IQA (PFIQA)
PFIQA outperforms current state-of-the-art models across three widely-used SR-IQA benchmarks.
arXiv Detail & Related papers (2024-05-15T16:09:22Z) - Efficient Test-Time Adaptation for Super-Resolution with Second-Order
Degradation and Reconstruction [62.955327005837475]
Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images.
We present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types.
arXiv Detail & Related papers (2023-10-29T13:58:57Z) - RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive
Feature Alignment and Selection [66.08293086254851]
We propose a reciprocal learning framework to reinforce the learning of a RefSR network.
The newly proposed module aligns reference-input images at multi-scale feature spaces and performs reference-aware feature selection.
We empirically show that multiple recent state-of-the-art RefSR models can be consistently improved with our reciprocal learning paradigm.
arXiv Detail & Related papers (2022-11-08T12:39:35Z) - QMRNet: Quality Metric Regression for EO Image Quality Assessment and
Super-Resolution [2.425299069769717]
We benchmark state-of-the-art Super-Resolution (SR) algorithms for distinct Earth Observation (EO) datasets.
We also propose a novel Quality Metric Regression Network (QMRNet) that is able to predict quality (as a No-Reference metric) by training on any property of the image.
Overall benchmark shows promising results for LIIF, CAR and MSRN and also the potential use of QMRNet as Loss for optimizing SR predictions.
arXiv Detail & Related papers (2022-10-12T22:51:13Z) - Exploring Resolution and Degradation Clues as Self-supervised Signal for
Low Quality Object Detection [77.3530907443279]
We propose a novel self-supervised framework to detect objects in degraded low resolution images.
Our methods has achieved superior performance compared with existing methods when facing variant degradation situations.
arXiv Detail & Related papers (2022-08-05T09:36:13Z) - Textural-Structural Joint Learning for No-Reference Super-Resolution
Image Quality Assessment [59.91741119995321]
We develop a dual stream network to jointly explore the textural and structural information for quality prediction, dubbed TSNet.
By mimicking the human vision system (HVS) that pays more attention to the significant areas of the image, we develop the spatial attention mechanism to make the visual-sensitive areas more distinguishable.
Experimental results show the proposed TSNet predicts the visual quality more accurate than the state-of-the-art IQA methods, and demonstrates better consistency with the human's perspective.
arXiv Detail & Related papers (2022-05-27T09:20:06Z) - Image Quality Assessment using Contrastive Learning [50.265638572116984]
We train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem.
We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models.
Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets.
arXiv Detail & Related papers (2021-10-25T21:01:00Z) - ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution [0.0]
ERQA metric aims to estimate a model's ability to restore real details using VSR.
Code for the proposed metric is publicly available at https://github.com/msu-video-group/ERQA.
arXiv Detail & Related papers (2021-10-19T14:04:16Z) - Learning-Based Quality Assessment for Image Super-Resolution [25.76907513611358]
We build a large-scale SR image database using a novel semi-automatic labeling approach.
The resulting SR Image quality database contains 8,400 images of 100 natural scenes.
We train an end-to-end Deep Image SR Quality (DISQ) model by employing two-stream Deep Neural Networks (DNNs) for feature extraction, followed by a feature fusion network for quality prediction.
arXiv Detail & Related papers (2020-12-16T04:06:27Z) - Characteristic Regularisation for Super-Resolving Face Images [81.84939112201377]
Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery.
Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data.
This renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution.
We formulate a method that joins the advantages of conventional SR and UDA models.
arXiv Detail & Related papers (2019-12-30T16:27:24Z)
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.