Denoising
1835 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.
SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model
In this paper, we propose SingularTrajectory, a diffusion-based universal trajectory prediction framework to reduce the performance gap across the five tasks.
Ship in Sight: Diffusion Models for Ship-Image Super Resolution
In this context, our method explores in depth the problem of ship image super resolution, which is crucial for coastal and port surveillance.
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration.
Noise2Noise Denoising of CRISM Hyperspectral Data
Hyperspectral data acquired by the Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) have allowed for unparalleled mapping of the surface mineralogy of Mars.
Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model
Specifically, we inject the priors into the denoising model to improve the utilization of reference information in unchanged areas and regulate the reconstruction of semantically relevant content in changed areas.
Denoising Table-Text Retrieval for Open-Domain Question Answering
Previous studies in table-text open-domain question answering have two common challenges: firstly, their retrievers can be affected by false-positive labels in training datasets; secondly, they may struggle to provide appropriate evidence for questions that require reasoning across the table.
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework
We adopt a two-stage training strategy for the diffusion model, effectively binding movements with specific appearances.
Multi-Scale Texture Loss for CT denoising with GANs
To grasp highly complex and non-linear textural relationships in the training process, this work presents a loss function that leverages the intrinsic multi-scale nature of the Gray-Level-Co-occurrence Matrix (GLCM).
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation
Our approach is motivated by the observation that different degradation types impact the image content on different frequency subbands, thereby requiring different treatments for each restoration task.