DeepAI AI Chat
Log In Sign Up

Reliability-based Mesh-to-Grid Image Reconstruction

by   Ján Koloda, et al.

This paper presents a novel method for the reconstruction of images from samples located at non-integer positions, called mesh. This is a common scenario for many image processing applications, such as super-resolution, warping or virtual view generation in multi-camera systems. The proposed method relies on a set of initial estimates that are later refined by a new reliability-based content-adaptive framework that employs denoising in order to reduce the reconstruction error. The reliability of the initial estimate is computed so stronger denoising is applied to less reliable estimates. The proposed technique can improve the reconstruction quality by more than 2 dB (in terms of PSNR) with respect to the initial estimate and it outperforms the state-of-the-art denoising-based refinement by up to 0.7 dB.


page 3

page 4


Denoising-based image reconstruction from pixels located at non-integer positions

Digital images are commonly represented as regular 2D arrays, so pixels ...

Variational local structure estimation for image super-resolution

Super-resolution is an important but difficult problem in image/video pr...

ADIR: Adaptive Diffusion for Image Reconstruction

In recent years, denoising diffusion models have demonstrated outstandin...

Mesh-based Camera Pairs Selection and Occlusion-Aware Masking for Mesh Refinement

Many Multi-View-Stereo algorithms extract a 3D mesh model of a scene, af...

Facetwise Mesh Refinement for Multi-View Stereo

Mesh refinement is a fundamental step for accurate Multi-View Stereo. It...

Estimating Discretization Error with Preset Orders of Accuracy and Fractional Refinement Ratios

In solution verification, the primary goal is finding an accurate and re...

A Novel Viewport-Adaptive Motion Compensation Technique for Fisheye Video

Although fisheye cameras are in high demand in many application areas du...