Back to search

Georgia Institute of Technology

Differentiable 3D Scene Representations with Point-based Neural Methods

Abstract

dc:description.abstract

This thesis explores particle-based approaches for scene representation. We introduce moving patches by fitting geometry pixels ("gexels") of moving geometry images onto the scene geometry. We propose to represent a signed distance field as a weighted sum of local functions attached to moving particles. We consider optimization frameworks to fit both 2D and 3D target shapes and propose a splitting strategy to control the density of particles. Experiments on canonical 3D models demonstrate our method’s viability to capture coarse and fine geometric structures with explainable local patches, offering a storage‑efficient alternative to current representations. Finally, we outline avenues for future work, such as continuous neural patch parametrization, adaptive domain decomposition, and interactive editing. We hope to inspire further investigation into explainable, flexible, and differentiable explicit geometry paradigms that balance fidelity, efficiency and editability.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Interactive Computing
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Borcsok, Barnabas Barney
Advisors dc:contributor.advisor
  • Zhu, Bo
  • Turk, Greg
Committee member dc:contributor.committeemember
  • Ha, Sehoon

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/77851

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Borcsok, Barnabas Barney. Differentiable 3D Scene Representations with Point-based Neural Methods. Masters thesis, Georgia Institute of Technology, 2025. https://hdl.handle.net/1853/77851