SOTAVerified

Denoising

Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.

( Image credit: Beyond a Gaussian Denoiser )

Papers

Showing 2650 of 7282 papers

TitleStatusHype
Cameras as Rays: Pose Estimation via Ray DiffusionCode4
PharMolixFM: All-Atom Foundation Models for Molecular Modeling and GenerationCode4
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language ModelsCode4
FSID: Fully Synthetic Image Denoising via Procedural Scene GenerationCode4
Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian NoiseCode4
Energy-Based Transformers are Scalable Learners and ThinkersCode4
PromptFix: You Prompt and We Fix the PhotoCode4
Simple Baselines for Image RestorationCode4
OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion ModelsCode4
MotionClone: Training-Free Motion Cloning for Controllable Video GenerationCode4
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense PredictionCode4
DiffusionDet: Diffusion Model for Object DetectionCode4
Diffusion Models for Medical Image Analysis: A Comprehensive SurveyCode4
One Step Diffusion via Shortcut ModelsCode4
DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR ImagesCode4
Diffusion Model-Based Image Editing: A SurveyCode4
AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video DataCode4
DiffBIR: Towards Blind Image Restoration with Generative Diffusion PriorCode4
Adversarial Diffusion Compression for Real-World Image Super-ResolutionCode4
Diffusion Models in Low-Level Vision: A SurveyCode4
AsyncDiff: Parallelizing Diffusion Models by Asynchronous DenoisingCode4
VideoFusion: Decomposed Diffusion Models for High-Quality Video GenerationCode4
High-Resolution Image Synthesis with Latent Diffusion ModelsCode4
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code GenerationCode4
InstructIR: High-Quality Image Restoration Following Human InstructionsCode4
Show:102550
← PrevPage 2 of 292Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SINDyPSNR81Unverified
2Pixel-shuffling DownsamplingPSNR38.4Unverified
3TWSCPSNR37.93Unverified
4CBDNet(Syn)PSNR37.57Unverified
5MCWNNMPSNR37.38Unverified
6Han et alPSNR35.95Unverified
7FFDNetPSNR34.4Unverified
8TNRDPSNR33.65Unverified
9CDnCNN-BPSNR32.43Unverified
10NLRNPSNR30.8Unverified
#ModelMetricClaimedVerifiedStatus
1DRUnet_Poisson_0.01Average PSNR (dB)33.92Unverified
#ModelMetricClaimedVerifiedStatus
1DRANetAverage PSNR39.64Unverified
#ModelMetricClaimedVerifiedStatus
1PCNN+RL+HMEAverage84.61Unverified