Image Enhancement

Image Enhancement is basically improving the interpretability or perception of information in images for human viewers and providing ‘better’ input for other automated image processing techniques. The principal objective of Image Enhancement is to modify attributes of an image to make it more suitable for a given task and a specific observer.

Source: A Comprehensive Review of Image Enhancement Techniques

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 811–820 of 983 papers

Title	Date	Tasks	Status	Hype
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement	Jan 19, 2020	Color ConstancyFace Detection	CodeCode Available	1
Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey	Jan 8, 2020	Autonomous NavigationDecision Making	—Unverified	0
Supervised and Unsupervised Learning of Parameterized Color Enhancement	Dec 30, 2019	Image EnhancementTranslation	—Unverified	0
Self-supervised Fine-tuning for Correcting Super-Resolution Convolutional Neural Networks	Dec 30, 2019	Image EnhancementSuper-Resolution	—Unverified	0
Image Enhanced Rotation Prediction for Self-Supervised Learning	Dec 25, 2019	Image EnhancementObject	—Unverified	0
Σ-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction	Dec 18, 2019	Image EnhancementImage Reconstruction	CodeCode Available	0
Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software	Dec 17, 2019	Image Enhancementreinforcement-learning	—Unverified	0
A hierarchical approach to deep learning and its application to tomographic reconstruction	Dec 16, 2019	Computational EfficiencyComputed Tomography (CT)	—Unverified	0
Adaptive GNN for Image Analysis and Editing	Dec 1, 2019	Graph Neural NetworkImage Enhancement	—Unverified	0
CURL: Neural Curve Layers for Global Image Enhancement	Nov 29, 2019	DecoderDemosaicking	CodeCode Available	0

Show:10 25 50

← PrevPage 82 of 99Next →

All datasets MIT-Adobe 5k TIP 2018 Exposure-Errors MIT-Adobe FiveK SICE-Grad SICE-Mix

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	HG-MTFE	PSNR on proRGB	25.69	—	Unverified
2	PQDynamicISP	PSNR on proRGB	25.53	—	Unverified
3	RSFNet-map	PSNR on proRGB	25.49	—	Unverified
4	AdaInt	PSNR on proRGB	25.49	—	Unverified
5	SepLUT	PSNR on proRGB	25.47	—	Unverified
6	MTFE	PSNR on proRGB	25.46	—	Unverified
7	3D LUT	PSNR on proRGB	25.21	—	Unverified
8	Retinexformer	PSNR on sRGB	24.94	—	Unverified
9	4D LUT	PSNR on proRGB	24.61	—	Unverified
10	DIFAR (MSCA, level 1)	PSNR on proRGB	24.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ESDNet-L	PSNR	30.11	—	Unverified
2	MBCNN	PSNR	30.03	—	Unverified
3	ESDNet	PSNR	29.81	—	Unverified
4	Uformer-B	PSNR	29.28	—	Unverified
5	MopNet	PSNR	27.75	—	Unverified
6	DMCNN	PSNR	26.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Exposure-slot	PSNR	23.18	—	Unverified
2	CSEC	PSNR	22.73	—	Unverified
3	LCDPNet	PSNR	22.17	—	Unverified
4	IAT	PSNR	20.34	—	Unverified
5	MSEC	PSNR	20.21	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TreEnhance	DeltaE	11.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CIDNet	Average PSNR	13.45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CIDNet	Average PSNR	13.43	—	Unverified