Image Denoising
416 papers with code • 19 benchmarks • 17 datasets
Image Denoising is a computer vision task that involves removing noise from an image. Noise can be introduced into an image during acquisition or processing, and can reduce image quality and make it difficult to interpret. Image denoising techniques aim to restore an image to its original quality by reducing or removing the noise, while preserving the important features of the image.
( Image credit: Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior )
Benchmarks
These leaderboards are used to track progress in Image Denoising
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Image Denoising models and implementations
FFHQ
BSD
Urban100
SIDD
SID
CBSD68
PolyU
DND
CRVD
ELD
Latest papers
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
woldier/witunet
•
•
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.
NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Datase
ronjonxu/naid
•
•
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.
TBSN: Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
For channel self-attention, we observe that it may leak the blind-spot information when the channel number is greater than spatial size in the deep layers of multi-scale architectures.
Spatio-Spectral Structure Tensor Total Variation for Hyperspectral Image Denoising and Destriping
However, since SSTV refers only to adjacent pixels/bands, semi-local spatial structures are not preserved during denoising process.
Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration
All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation.
SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder
We employ our method to generate paired training samples for real-world image denoising and super-resolution tasks.
IIDM: Image-to-Image Diffusion Model for Semantic Image Synthesis
Semantic image synthesis aims to generate high-quality images given semantic conditions, i. e. segmentation masks and style reference images.
Hybrid Convolutional and Attention Network for Hyperspectral Image Denoising
summitgao/hcanet
•
•
To enhance the modeling of both global and local features, we have devised a convolution and attention fusion module aimed at capturing long-range dependencies and neighborhood spectral correlations.
Iterative Learning for Joint Image Denoising and Motion Artifact Correction of 3D Brain MRI
goodaycoder/jdac
•
•
To address these issues, we propose a Joint image Denoising and motion Artifact Correction (JDAC) framework via iterative learning to handle noisy MRIs with motion artifacts, consisting of an adaptive denoising model and an anti-artifact model.
Beyond Text: Frozen Large Language Models in Visual Signal Comprehension
To achieve this, we present the Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, which transforms an image into a ``foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model.
