Image Super-Resolution

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.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1411–1420 of 1589 papers

Title	Date	Tasks	Status	Hype
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks	Sep 1, 2018	Face HallucinationGenerative Adversarial Network	CodeCode Available	3
Learning Sparse Low-Precision Neural Networks With Learnable Regularization	Sep 1, 2018	Image Super-ResolutionL2 Regularization	—Unverified	0
Wide Activation for Efficient and Accurate Image Super-Resolution	Aug 27, 2018	Image Super-ResolutionMulti-Frame Super-Resolution	CodeCode Available	0
Efficient Single Image Super Resolution using Enhanced Learned Group Convolutions	Aug 26, 2018	Image Super-ResolutionSuper-Resolution	CodeCode Available	0
Deep Learning for Single Image Super-Resolution: A Brief Review	Aug 9, 2018	Deep LearningEfficient Neural Network	CodeCode Available	0
Brain MRI Image Super Resolution using Phase Stretch Transform and Transfer Learning	Jul 31, 2018	HallucinationImage Super-Resolution	CodeCode Available	0
The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution	Jul 31, 2018	General ClassificationImage Reconstruction	CodeCode Available	1
To learn image super-resolution, use a GAN to learn how to do image degradation first	Jul 30, 2018	Generative Adversarial NetworkImage Super-Resolution	CodeCode Available	0
Gated Fusion Network for Joint Image Deblurring and Super-Resolution	Jul 27, 2018	Computational EfficiencyDeblurring	CodeCode Available	0
Perceptual Video Super Resolution with Enhanced Temporal Consistency	Jul 20, 2018	Image Super-ResolutionSuper-Resolution	—Unverified	0

Show:10 25 50

← PrevPage 142 of 159Next →

All datasets Set14 - 4x upscaling BSD100 - 4x upscaling Urban100 - 4x upscaling Manga109 - 4x upscaling Set5 - 2x upscaling Set14 - 2x upscaling Set5 - 3x upscaling BSD100 - 2x upscaling Urban100 - 2x upscaling Set14 - 3x upscaling Urban100 - 3x upscaling BSD100 - 3x upscaling

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DRCT-L	PSNR	29.54	—	Unverified
2	HMA†	PSNR	29.51	—	Unverified
3	Hi-IR-L	PSNR	29.49	—	Unverified
4	HAT-L	PSNR	29.47	—	Unverified
5	HAT_FIR	PSNR	29.44	—	Unverified
6	DRCT	PSNR	29.4	—	Unverified
7	HAT	PSNR	29.38	—	Unverified
8	SwinFIR	PSNR	29.36	—	Unverified
9	CPAT+	PSNR	29.36	—	Unverified
10	CPAT	PSNR	29.34	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DRCT-L	PSNR	28.16	—	Unverified
2	HMA†	PSNR	28.13	—	Unverified
3	Hi-IR-L	PSNR	28.13	—	Unverified
4	HAT-L	PSNR	28.09	—	Unverified
5	HAT_FIR	PSNR	28.07	—	Unverified
6	CPAT+	PSNR	28.06	—	Unverified
7	DRCT	PSNR	28.06	—	Unverified
8	HAT	PSNR	28.05	—	Unverified
9	CPAT	PSNR	28.04	—	Unverified
10	SwinFIR	PSNR	28.03	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Hi-IR-L	PSNR	28.72	—	Unverified
2	DRCT-L	PSNR	28.7	—	Unverified
3	HMA†	PSNR	28.69	—	Unverified
4	HAT-L	PSNR	28.6	—	Unverified
5	HAT_FIR	PSNR	28.43	—	Unverified
6	DRCT	PSNR	28.4	—	Unverified
7	HAT	PSNR	28.37	—	Unverified
8	CPAT+	PSNR	28.33	—	Unverified
9	CPAT	PSNR	28.22	—	Unverified
10	PFT	PSNR	28.2	—	Unverified