2026-09-23T05:54:41Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/120235 2023-09-05 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Hoiem, Derek Hoiem, Derek Golparvar-Fard, Mani Forsyth, David Furukawa, Yasutaka 2023-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms The student, Raj Kataria, accepted the attached license on 2023-04-04 at 17:32. The student, Raj Kataria, submitted this Dissertation for approval on 2023-04-04 at 17:40. This Dissertation was approved for publication on 2023-04-05 at 15:56. DSpace SAF Submission Ingestion Package generated from Vireo submission #18921 on 2023-09-01 at 17:07:59 Improving robustness of 3D reconstruction for sparse captures and challenging environments Kataria, Raj 2023-04-05 Structure From Motion Sfm Multi-view Stereo Mvs 3d Vision 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. Thesis eng https://hdl.handle.net/2142/120235 Copyright 2023 Raj Kataria Ph.D. Dissertation Computer Science University of Illinois at Urbana-Champaign Computer Science