Skip to Main Content
The paper targets denoising of multi-view images with both intra-view and inter-view redundancy exploited under the guidance of 3-D geometry constraints. A graphical model of surface patches from each view of the multi-view image sequence is proposed to model the redundancy more effectively and efficiently. Patches are clustered according to their similarities between each other measured by the geodesic distance on the graph. Noises are attenuated via Wiener filtering on the sparse representations transformed by DCT of these patches. The graphical model is first used in image denoising and outperforms the state-of-the-art de-noising methods on the multi-view image sequence because the model fits the feature of the two kinds of redundancy very well. Furthermore, the 3-D model reconstructed from multi-view images denoised by our method is more accurate and complete compared with those reconstructed from denoised images by other methods.