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 51100 of 7282 papers

TitleStatusHype
Simple Baselines for Image RestorationCode4
RePaint: Inpainting using Denoising Diffusion Probabilistic ModelsCode4
High-Resolution Image Synthesis with Latent Diffusion ModelsCode4
Discrete Diffusion in Large Language and Multimodal Models: A SurveyCode3
Training-Free Efficient Video Generation via Dynamic Token CarvingCode3
dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive CachingCode3
PixelHacker: Image Inpainting with Structural and Semantic ConsistencyCode3
Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted ConceptsCode3
DDT: Decoupled Diffusion TransformerCode3
Optimal Stepsize for Diffusion SamplingCode3
Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal ConsistencyCode3
GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous DrivingCode3
Attention Distillation: A Unified Approach to Visual Characteristics TransferCode3
AnyTop: Character Animation Diffusion with Any TopologyCode3
SoftVQ-VAE: Efficient 1-Dimensional Continuous TokenizerCode3
Around the World in 80 Timesteps: A Generative Approach to Global Visual GeolocationCode3
Advanced Video Inpainting Using Optical Flow-Guided Efficient DiffusionCode3
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse ViewsCode3
3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D GenerationCode3
AP-LDM: Attentive and Progressive Latent Diffusion Model for Training-Free High-Resolution Image GenerationCode3
Diffusion Models are Evolutionary AlgorithmsCode3
LinFusion: 1 GPU, 1 Minute, 16K ImageCode3
Scaling Diffusion Transformers to 16 Billion ParametersCode3
Instruct-IPT: All-in-One Image Processing Transformer via Weight ModulationCode3
Director3D: Real-world Camera Trajectory and 3D Scene Generation from TextCode3
VideoTetris: Towards Compositional Text-to-Video GenerationCode3
Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference OptimizationCode3
Proxy Denoising for Source-Free Domain AdaptationCode3
Reservoir History Matching of the Norne field with generative exotic priors and a coupled Mixture of Experts -- Physics Informed Neural Operator Forward ModelCode3
MotionFollower: Editing Video Motion via Lightweight Score-Guided DiffusionCode3
On the Trajectory Regularity of ODE-based Diffusion SamplingCode3
UnMarker: A Universal Attack on Defensive Image WatermarkingCode3
Taming Stable Diffusion for Text to 360° Panorama Image GenerationCode3
Self-Rectifying Diffusion Sampling with Perturbed-Attention GuidanceCode3
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation FrameworkCode3
Physics-Informed Diffusion ModelsCode3
ReNoise: Real Image Inversion Through Iterative NoisingCode3
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and ModulationCode3
Multimodal-Conditioned Latent Diffusion Models for Fashion Image EditingCode3
Scaling Diffusion Models to Real-World 3D LiDAR Scene CompletionCode3
VmambaIR: Visual State Space Model for Image RestorationCode3
Score-Guided Diffusion for 3D Human RecoveryCode3
Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force FieldsCode3
Diffusion-TS: Interpretable Diffusion for General Time Series GenerationCode3
ViewDiff: 3D-Consistent Image Generation with Text-to-Image ModelsCode3
Seamless Human Motion Composition with Blended Positional EncodingsCode3
Visual Style Prompting with Swapping Self-AttentionCode3
3D Diffuser Actor: Policy Diffusion with 3D Scene RepresentationsCode3
3D Diffuser Actor: Policy Diffusion with 3D Scene RepresentationsCode3
RoHM: Robust Human Motion Reconstruction via DiffusionCode3
Show:102550
← PrevPage 2 of 146Next →

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