Image Super-Resolution

596 papers with code • 61 benchmarks • 39 datasets

Image Super-Resolution is a machine learning task where the goal is to increase the resolution of an image, often by a factor of 4x or more, while maintaining its content and details as much as possible. The end result is a high-resolution version of the original image. This task can be used for various applications such as improving image quality, enhancing visual detail, and increasing the accuracy of computer vision algorithms.

Libraries

Use these libraries to find Image Super-Resolution models and implementations

CFAT: Unleashing TriangularWindows for Image Super-resolution

rayabhisek123/cfat 24 Mar 2024

To overcome these weaknesses, we propose a non-overlapping triangular window technique that synchronously works with the rectangular one to mitigate boundary-level distortion and allows the model to access more unique sifting modes.

5
24 Mar 2024

Efficient scene text image super-resolution with semantic guidance

sijieliu518/sgenet 20 Mar 2024

Scene text image super-resolution has significantly improved the accuracy of scene text recognition.

5
20 Mar 2024

VmambaIR: Visual State Space Model for Image Restoration

alphacatplus/vmambair 18 Mar 2024

To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks.

92
18 Mar 2024

Adaptive Semantic-Enhanced Denoising Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution

littlebeen/asddpm-adaptive-semantic-enhanced-ddpm 17 Mar 2024

However, the high-frequency details generated by DDPM often suffer from misalignment with HR images due to the model's tendency to overlook long-range semantic contexts.

6
17 Mar 2024

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

mhamilton723/FeatUp 15 Mar 2024

Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime.

786
15 Mar 2024

BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-Resolution

lifengcs/blinddiff 15 Mar 2024

BlindDiff seamlessly integrates the MAP-based optimization into DMs, which constructs a joint distribution of the low-resolution (LR) observation, high-resolution (HR) data, and degradation kernels for the data and kernel priors, and solves the blind SR problem by unfolding MAP approach along with the reverse process.

6
15 Mar 2024

Efficient Diffusion Model for Image Restoration by Residual Shifting

zsyoaoa/resshift 12 Mar 2024

While diffusion-based image restoration (IR) methods have achieved remarkable success, they are still limited by the low inference speed attributed to the necessity of executing hundreds or even thousands of sampling steps.

463
12 Mar 2024

Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution

dreamzz5/simple-align 29 Feb 2024

Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years.

29
29 Feb 2024

SeD: Semantic-Aware Discriminator for Image Super-Resolution

lbc12345/sed 29 Feb 2024

In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner.

15
29 Feb 2024

Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts

mandalinadagi/wgsr 29 Feb 2024

Although some recent works focused on the differentiation of details and artifacts, this is a very challenging problem and a satisfactory solution is yet to be found.

13
29 Feb 2024