SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 651–675 of 983 papers

TitleStatusHype
Domain Adaptation for Underwater Image EnhancementCode0
Single Underwater Image Enhancement Using an Analysis-Synthesis Network—0
Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables—0
Guided Colorization Using Mono-Color Image Pairs—0
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the DarkCode1
Rain Removal and Illumination Enhancement Done in One Go—0
A guided edge-aware smoothing-sharpening filter based on patch interpolation model and generalized Gamma distributionCode1
Exploring Low-light Object Detection Techniques—0
Single image deep defocus estimation and its applicationsCode0
Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement—0
StarEnhancer: Learning Real-Time and Style-Aware Image EnhancementCode1
3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical ImagesCode1
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image EnhancementCode1
1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition—0
Intrinsic Image Transfer for Illumination ManipulationCode0
BLNet: A Fast Deep Learning Framework for Low-Light Image Enhancement with Noise Removal and Color RestorationCode0
R2RNet: Low-light Image Enhancement via Real-low to Real-normal NetworkCode1
Zero-Shot Single Image Restoration Through Controlled Perturbation of Koschmieder's Model—0
Automated Log-Scale Quantization for Low-Cost Deep Neural Networks—0
Restoring Extremely Dark Images in Real TimeCode0
Debiased Subjective Assessment of Real-World Image Enhancement—0
Removal of speckle noises from ultrasound images using five different deep learning networksCode0
User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning—0
NLHD: A Pixel-Level Non-Local Retinex Model for Low-Light Image Enhancement—0
Evaluating Deep Neural Networks for Image Document Enhancement—0
Show:102550
← PrevPage 27 of 40Next →
All datasetsMIT-Adobe 5kTIP 2018Exposure-ErrorsMIT-Adobe FiveKSICE-GradSICE-Mix

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HG-MTFEPSNR on proRGB25.69—Unverified
2PQDynamicISPPSNR on proRGB25.53—Unverified
3RSFNet-mapPSNR on proRGB25.49—Unverified
4AdaIntPSNR on proRGB25.49—Unverified
5SepLUTPSNR on proRGB25.47—Unverified
6MTFEPSNR on proRGB25.46—Unverified
73D LUTPSNR on proRGB25.21—Unverified
8RetinexformerPSNR on sRGB24.94—Unverified
94D LUTPSNR on proRGB24.61—Unverified
10DIFAR (MSCA, level 1)PSNR on proRGB24.2—Unverified
#ModelMetricClaimedVerifiedStatus
1ESDNet-LPSNR30.11—Unverified
2MBCNNPSNR30.03—Unverified
3ESDNetPSNR29.81—Unverified
4Uformer-BPSNR29.28—Unverified
5MopNetPSNR27.75—Unverified
6DMCNNPSNR26.77—Unverified
#ModelMetricClaimedVerifiedStatus
1Exposure-slotPSNR23.18—Unverified
2CSECPSNR22.73—Unverified
3LCDPNetPSNR22.17—Unverified
4IATPSNR20.34—Unverified
5MSECPSNR20.21—Unverified
#ModelMetricClaimedVerifiedStatus
1TreEnhanceDeltaE11.25—Unverified
#ModelMetricClaimedVerifiedStatus
1CIDNetAverage PSNR13.45—Unverified
#ModelMetricClaimedVerifiedStatus
1CIDNetAverage PSNR13.43—Unverified