Back to search

Cornell University

Robustly Modeling The World From Photos

Abstract

dc:description.abstract

A camera is a device for compressing rich information about the visual appearance of the three-dimensional world into a two-dimensional image. This process is inherently lossy: given an image, we can make educated guesses about the world's shape and appearance, but there is not enough information for our guesses to be certain. However, if we take several pictures from different viewpoints we can reason more confidently. This thesis focuses on shape: How can we determine the geometry of the world from a collection of photos? This problem is classically called Structure from Motion. We find the structure (shape of the world) from camera motion (different viewpoints). Internet photo collections are an especially interesting source of data. With simple searches we can collect the raw information to reconstruct 3D models of famous world landmarks or entire cities. However, the photos we download are disorganized and noisy, and will not have been collected with 3D reconstruction in mind. While some impressive demonstrations of Structure from Motion systems exist, the next generation of solvers will need to be far more robust to the many types of difficulties encountered in the wild. To this end, many recent solvers pose the problem in a new way, using relative relationships between images to infer first the orientations, and then the positions of every camera in a scene. This framework promises faster runtime and greater robustness. I contribute a theoretical analysis of the difficulty of finding camera orientations, giving a way to decide which problems are tractable and which ones might be too hard and should be reformulated. I also propose a new solver with an accompanying outlier filter for finding camera positions. However, some of the hardest scenes are those which contain ambiguous structures: objects that look the same but are not. These induce self-consistent errors which are often too confusing for solvers to resolve correctly. I describe a scalable system which uses a graph-topological cue from a visibility graph to detect and remove these sources of error. Together these improvements work towards a robust solution to the Structure from Motion problem, so that we can reliably build 3D models of the world, even from noisy and confusing internet photo collections.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Applied Mathematics
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Applied Mathematics
Grantor
Cornell University
Year dc:date.issued
2016

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wilson, Kyle
Chair dc:contributor.chair
  • Snavely,Keith Noah
Committee members dc:contributor.committeemember
  • Connelly,Robert
  • Bindel,David S.
  • Bala,Kavita

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Dc Identifier Bibid
9597134

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Wilson, Kyle. Robustly Modeling The World From Photos. Doctor of Philosophy thesis, Cornell University, 2016. https://hdl.handle.net/1813/44330