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 176200 of 7282 papers

TitleStatusHype
Omegance: A Single Parameter for Various Granularities in Diffusion-Based SynthesisCode2
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion ModelsCode2
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache SharingCode2
V2X-R: Cooperative LiDAR-4D Radar Fusion for 3D Object Detection with Denoising DiffusionCode2
X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenariosCode2
Consistency Diffusion Bridge ModelsCode2
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse AutoencodersCode2
Retrieval-Augmented Diffusion Models for Time Series ForecastingCode2
Diffusion Transformer PolicyCode2
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video GenerationCode2
High-Precision Dichotomous Image Segmentation via Probing Diffusion CapacityCode2
Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion ModelsCode2
Training-Free Adaptive Diffusion with Bounded Difference Approximation StrategyCode2
Reconstructive Visual Instruction TuningCode2
Progressive Autoregressive Video Diffusion ModelsCode2
Think While You Generate: Discrete Diffusion with Planned DenoisingCode2
Towards Ultra-Low-Power Neuromorphic Speech Enhancement with Spiking-FullSubNetCode2
DeFoG: Discrete Flow Matching for Graph GenerationCode2
Learning Truncated Causal History Model for Video RestorationCode2
PnP-Flow: Plug-and-Play Image Restoration with Flow MatchingCode2
Conditional Image Synthesis with Diffusion Models: A SurveyCode2
DualDn: Dual-domain Denoising via Differentiable ISPCode2
Cross-video Identity Correlating for Person Re-identification Pre-trainingCode2
HSIGene: A Foundation Model For Hyperspectral Image GenerationCode2
EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidanceCode2
Show:102550
← PrevPage 8 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