Honors Theses

Date of Award

Spring 5-7-2026

Document Type

Undergraduate Thesis

Department

Computer and Information Science

First Advisor

David Harrison

Second Advisor

Yixin Chen

Relational Format

Dissertation/Thesis

Abstract

Signal simulation environments require accurate three dimensional representations of physical spaces, yet current methods for generating these representations, including Light Detection and Ranging (LiDAR) scanning, manual 3D modeling, and commercial photogrammetry, are both costly and time intensive. SpaceForge addresses this gap with a prompt guided pipeline that takes an ordinary indoor photograph and a configurable set of simulation relevant object categories as input and produces a voxelized 3D scene compatible with downstream signal simulation workflows. The pipeline proceeds through five major stages: open set object detection and segmentation, object level preprocessing, single image 3D mesh reconstruction, heuristic pose estimation and scene assembly, and voxelization of the complete scene point cloud. Room geometry, floor, walls, and ceiling, is estimated from the assembled furniture layout and merged into the scene before voxelization, producing a regular voxel grid saved in multiple formats for downstream use. The completed pipeline runs end to end from a single command line call with no manual intervention, completing a typical indoor scene in approximately two to four minutes on a capable GPU.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.