SOTAVerified

Demosaicking

Most modern digital cameras acquire color images by measuring only one color channel per pixel, red, green, or blue, according to a specific pattern called the Bayer pattern. Demosaicking is the processing step that reconstruct a full color image given these incomplete measurements.

Source: Revisiting Non Local Sparse Models for Image Restoration

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 150 papers

TitleStatusHype
Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot—0
Deep Learning Approach for Hyperspectral Image Demosaicking, Spectral Correction and High-resolution RGB Reconstruction—0
Del-Net: A Single-Stage Network for Mobile Camera ISP—0
Demosaicing and Superresolution for Color Filter Array via Residual Image Reconstruction and Sparse Representation—0
Discriminative Transfer Learning for General Image Restoration—0
Efficient and Accurate Hyperspectral Image Demosaicing with Neural Network Architectures—0
Learning Deep Convolutional Networks for Demosaicing—0
Learning Degradation-Independent Representations for Camera ISP Pipelines—0
Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization—0
Learning to Jointly Deblur, Demosaick and Denoise Raw Images—0
SDAT: Sub-Dataset Alternation Training for Improved Image Demosaicing—0
MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging—0
Megapixel Photon-Counting Color Imaging using Quanta Image Sensor—0
Merging-ISP: Multi-Exposure High Dynamic Range Image Signal Processing—0
Model-based demosaicking for acquisitions by a RGBW color filter array—0
Monochrome and Color Polarization Demosaicking Using Edge-Aware Residual Interpolation—0
MSFA-Frequency-Aware Transformer for Hyperspectral Images Demosaicing—0
Multispectral snapshot demosaicing via non-convex matrix completion—0
Multispectral Demosaicing via Dual Cameras—0
NeRD: Neural field-based Demosaicking—0
Neural Network Generalization: The impact of camera parameters—0
NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge—0
Optimizing Codes for Source Separation in Color Image Demosaicing and Compressive Video Recovery—0
Pixel-Inconsistency Modeling for Image Manipulation Localization—0
Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.