Improving robustness of 3D reconstruction for sparse captures and challenging environments

Kataria, Raj

Permalink

https://hdl.handle.net/2142/120235 Copy

Description

Title

Improving robustness of 3D reconstruction for sparse captures and challenging environments

Author(s)

Kataria, Raj

Issue Date

2023-04-05

Director of Research (if dissertation) or Advisor (if thesis)

Hoiem, Derek

Doctoral Committee Chair(s)

Hoiem, Derek

Committee Member(s)

• Golparvar-Fard, Mani
• Forsyth, David
• Furukawa, Yasutaka

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Structure from Motion
• SfM
• Multi-view Stereo
• MVS, 3D Vision

Abstract

The applications of 3D modeling in the world are ubiquitous. For example, the construction industry models ongoing projects to monitor progress. The housing industry uses 360 images to develop 3D floor plans to help customers visualize home interiors. These applications rely on real-world data that poses challenges for 3D modeling systems. In this dissertation, I will discuss the specific challenges that arise during the modeling process, and how we address them. First, images capture the scene of interest, which can be onerous as planned capture paths can result in reconstruction failures or yield incomplete models. Our feature track simulator uses a camera trajectory and scene geometry to evaluate planned paths prior to the collection process. Next, a structure from motion (SfM) system reconstructs the scene, and outputs camera parameters and image poses. Images that contain repeated or duplicate structures present ambiguities and can cause catastrophic failures in reconstruction. Our approach discounts matches on repeated structures and estimates correct poses using a set of reliable images in the resectioning process. Then, a multi-view stereo (MVS) system uses the camera parameters and image poses to generate a dense model. MVS systems require sufficient overlap between images for accurate depth estimation, which is often burdensome and costly. Our solution detects and completes planar surfaces with only one or two views, and circumvents the overlap requirement.

Graduation Semester

2023-05

Type of Resource

Thesis

Copyright and License Information

Copyright 2023 Raj Kataria

Owning Collections