InpaintFusion: Incremental RGB-D Inpainting for 3D Scenes

Shohei Mori, Okan Erat, Wolfgang Broll, Hideo Saito, Dieter Schmalstieg, Denis Kalkofen

Research output: Contribution to journalArticlepeer-review

Abstract

State-of-the-art methods for diminished reality propagate pixel information from a keyframe to subsequent frames for real-time inpainting. However, these approaches produce artifacts, if the scene geometry is not sufficiently planar. In this article, we present InpaintFusion, a new real-time method that extends inpainting to non-planar scenes by considering both color and depth information in the inpainting process. We use an RGB-D sensor for simultaneous localization and mapping, in order to both track the camera and obtain a surfel map in addition to RGB images. We use the RGB-D information in a cost function for both the color and the geometric appearance to derive a global optimization for simultaneous inpainting of color and depth. The inpainted depth is merged in a global map by depth fusion. For the final rendering, we project the map model into image space, where we can use it for effects such as relighting and stereo rendering of otherwise hidden structures. We demonstrate the capabilities of our method by comparing it to inpainting results with methods using planar geometric proxies.

Original languageEnglish
Article number9184389
Pages (from-to)2994 - 3007
Number of pages14
JournalIEEE Transactions on Visualization and Computer Graphics
Volume26
Issue number10
DOIs
Publication statusPublished - 1 Oct 2020

Keywords

  • Diminished reality
  • fusion
  • inpainting
  • SLAM

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'InpaintFusion: Incremental RGB-D Inpainting for 3D Scenes'. Together they form a unique fingerprint.

Cite this