Multiple View Image Denoising

This page can be viewed in Romanian (courtesy tranlation by Alexandra Seremina).


One of 25 input images with synthetic noise, PSNR=14.1471	Our 25-view denoising, PSNR=30.659

One of 25 input images with *real* noise, PSNR=28.6831	Our 25-view denoising, PSNR=44.1641

Abstract

We present a novel multi-view denoising algorithm. Our algorithm takes noisy images taken from different viewpoints as input and groups similar patches in the input images using depth estimation. We demonstrate the importance of modeling intensity-dependent noise in low-light conditions and how to to remove such noise using the principal component analysis and tensor analysis. The dimensionalities for both PCA and tensor analysis are automatically computed in a way that is adaptive to the complexity of image structures in the patches. Our method is based on a probabilistic formulation that marginalizes depth maps as hidden variables and therefore does not require perfect depth estimation. We validate our algorithm on both synthetic and real images with different content. Our algorithm compares favorably against several state-of-the-art denoising algorithms.

Paper

Li Zhang, Sundeep Vaddadi, Hailin Jin, and Shree Nayar, Multiple View Image Denoising, In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2009. [PDF(880K), Poster PDF (8.7M)]

Acknowledgement

This work is supported in part by Adobe System Incorporated and National Science Foundation IIS-0845916.

CVPR 2009 Additional Results

Gaussian Synthetic Noise

Croc Results

Evolve Results

Poisson Synthetic Noise

Real Image Noise