Thin Structures in Image Based Rendering - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Computer Graphics Forum Year : 2018

Thin Structures in Image Based Rendering

Abstract

We propose a novel method to handle thin structures in Image-Based Rendering (IBR), and specifically structures supported by simple geometric shapes such as planes, cylinders, etc. These structures, e.g. railings, fences, oven grills etc, are present in many man-made environments and are extremely challenging for multi-view 3D reconstruction, representing a major limitation of existing IBR methods. Our key insight is to exploit multi-view information. After a handful of user clicks to specify the supporting geometry, we compute multi-view and multi-layer alpha mattes to extract the thin structures. We use two multi-view terms in a graph-cut segmentation, the first based on multi-view foreground color prediction and the second ensuring multiview consistency of labels. Occlusion of the background can challenge reprojection error calculation and we use multiview median images and variance, with multiple layers of thin structures. Our end-to-end solution uses the multi-layer segmentation to create per-view mattes and the median colors and variance to create a clean background. We introduce a new multi-pass IBR algorithm based on depth-peeling to allow free-viewpoint navigation of multi-layer semi-transparent thin structures. Our results show significant improvement in rendering quality for thin structures compared to previous image-based rendering solutions.
Fichier principal
Vignette du fichier
main_thin_5.pdf (14.84 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01817948 , version 1 (18-06-2018)

Identifiers

  • HAL Id : hal-01817948 , version 1

Cite

Theo Thonat, Abdelaziz Djelouah, Fredo Durand, George Drettakis. Thin Structures in Image Based Rendering. Computer Graphics Forum, In press, 37. ⟨hal-01817948⟩
232 View
226 Download

Share

Gmail Facebook X LinkedIn More