Denoising
1901 papers with code • 5 benchmarks • 20 datasets
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 )
Libraries
Use these libraries to find Denoising models and implementationsSubtasks
Latest papers
ModWaveMLP: MLP-Based Mode Decomposition and Wavelet Denoising Model to Defeat Complex Structures in Traffic Forecasting
Additionally, when handling traffic data, researchers tend to manually design the model structure based on the data features, which makes the structure of traffic prediction redundant and the model generalizability limited.
CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method
Transforming large pre-trained low-resolution diffusion models to cater to higher-resolution demands, i. e., diffusion extrapolation, significantly improves diffusion adaptability.
CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task
In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images.
Collaborative Filtering Based on Diffusion Models: Unveiling the Potential of High-Order Connectivity
A recent study has shown that diffusion models are well-suited for modeling the generative process of user-item interactions in recommender systems due to their denoising nature.
Multi-Level Sequence Denoising with Cross-Signal Contrastive Learning for Sequential Recommendation
To the end, in this paper, we propose a novel model named Multi-level Sequence Denoising with Cross-signal Contrastive Learning (MSDCCL) for sequential recommendation.
A New Multi-Picture Architecture for Learned Video Deinterlacing and Demosaicing with Parallel Deformable Convolution and Self-Attention Blocks
We propose a new multi-picture architecture for video deinterlacing or demosaicing by aligning multiple supporting pictures with missing data to a reference picture to be reconstructed, benefiting from both local and global spatio-temporal correlations in the feature space using modified deformable convolution blocks and a novel residual efficient top-$k$ self-attention (kSA) block, respectively.
Molecular relaxation by reverse diffusion with time step prediction
As a remedy, we propose MoreRed, molecular relaxation by reverse diffusion, a conceptually novel and purely statistical approach where non-equilibrium structures are treated as noisy instances of their corresponding equilibrium states.
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy.
RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion
Accurate completion and denoising of roof height maps are crucial to reconstructing high-quality 3D buildings.
NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset
Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments.