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 125 of 7282 papers

TitleStatusHype
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingCode11
SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion TransformersCode9
LTX-Video: Realtime Video Latent DiffusionCode9
OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-onCode9
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image AnalysisCode7
Flow-GRPO: Training Flow Matching Models via Online RLCode7
M&M VTO: Multi-Garment Virtual Try-On and EditingCode7
One-Step Image Translation with Text-to-Image ModelsCode7
Improving Sample Quality of Diffusion Models Using Self-Attention GuidanceCode7
StreamDiffusion: A Pipeline-level Solution for Real-time Interactive GenerationCode6
Pseudo Numerical Methods for Diffusion Models on ManifoldsCode6
DanceGRPO: Unleashing GRPO on Visual GenerationCode5
FlowTok: Flowing Seamlessly Across Text and Image TokensCode5
OminiControl2: Efficient Conditioning for Diffusion TransformersCode5
StableAnimator: High-Quality Identity-Preserving Human Image AnimationCode5
DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous DrivingCode5
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You ThinkCode5
Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model LearningCode5
Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic SystemsCode5
IMAGDressing-v1: Customizable Virtual DressingCode5
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic AlignmentCode5
Controllable Generation with Text-to-Image Diffusion Models: A SurveyCode5
Ranni: Taming Text-to-Image Diffusion for Accurate Instruction FollowingCode5
DreamFusion: Text-to-3D using 2D DiffusionCode5
Energy-Based Transformers are Scalable Learners and ThinkersCode4
Show:102550
← PrevPage 1 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