Holistic 3D Reconstruction of Urban Structures from Low-Rank Textures

Mobahi, Hossein; Zhou, Zihan; Yang, Allen; Ma, Yi

Permalink

https://hdl.handle.net/2142/74358 Copy

Description

Title

Holistic 3D Reconstruction of Urban Structures from Low-Rank Textures

Author(s)

• Mobahi, Hossein
• Zhou, Zihan
• Yang, Allen
• Ma, Yi

Issue Date

2011-07

Keyword(s)

• Holistic
• 3D reconstruction
• Low-rank textures

Date of Ingest

• 2015-04-06T20:54:51Z
• 2017-07-14T22:54:57Z

Abstract

We introduce a new approach to reconstructing accurate camera geometry and 3D models for urban structures in a holistic fashion, i.e., without relying on extraction or matching of traditional local features such as points and edges. Instead, we use semi-global or global features based on transform invariant low-rank textures, which are ubiquitous in urban scenes. Modern high-dimensional optimization techniques enable us to accurately and robustly recover precise and consistent camera calibration and scene geometry from a single or multiple images of the scene. We demonstrate how to construct 3D models of real buildings from sequences of multiple large-baseline uncalibrated images that conventional SFM systems do not apply.

Publisher

Coordinated Science Laboratory, University of Illinois at Urbana-Champaign

Series/Report Name or Number

Coordinated Science Laboratory Report no. UILU-ENG-11-2205, DC-252

Type of Resource

text

Genre of Resource

Report (Grant or Annual)

Language

English

Permalink

http://hdl.handle.net/2142/74358

Sponsor(s)/Grant Number(s)

• National Science Foundation / NSF CCF 09-64215
• NAVY N00014-09-1-0230
• ARO MURI W911NF-06-1-0076
• ARL MAST-CTA W911NF-08-2-0004

Owning Collections