Denoising
1881 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 )
Benchmarks
These leaderboards are used to track progress in Denoising
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Denoising models and implementations
SIDD
SID
CBSD68
PolyU
DND
CRVD
iris
FMD
Subtasks
Latest papers
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.
Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Orthogonal Diffusion Models
Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models which are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing highly consistent multi-view images.
WcDT: World-centric Diffusion Transformer for Traffic Scene Generation
To enhance the scene diversity and stochasticity, the historical trajectory data is first preprocessed and encoded into latent space using Denoising Diffusion Probabilistic Models (DDPM) enhanced with Diffusion with Transformer (DiT) blocks.
OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments.
Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation
Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models.
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
Second, we propose a novel diffusion-based method that predicts a precise inpainting mask based on the person and reference garment images, further enhancing the reliability of the try-on results.
DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
The recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion.
CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models
The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech synthesis.
Denoising Distillation Makes Event-Frame Transformers as Accurate Gaze Trackers
Technically, we propose a two-stage learning-based gaze estimation framework to divide the whole gaze estimation process into a coarse-to-fine process of anchor state selection and final gaze location.
