{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/114812"},"canonical_url":"https://search.dev.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/114812","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"Geometry Processing with Neural Fields","abstract":"Geometry processing consists of algorithms for shape creation, manipulation, and analysis. These algorithms are cornerstones for the creation of almost every digital shapes. These shapes are consumed in our everyday lives, from digital contents to manufactured objects. These algorithms are indispensable parts of our every life. Traditionally, geometry processing algorithms are usually done with shape represented in explicit representations such as meshes, voxels, and their variants. These shape representations are easy to interpret by human, but they are difficult to be handled by automatic algorithms. For example, voxels can take up a lots of memory and meshes might need careful handle of the discretization quality during the processing. These challenges make development of geometry processing algorithms difficult and inefficient. In this thesis, we propose to use an alternative shape representation for the geometry processing pipeline. Specifically, each shape is represented by a neural network that takes a spatial coordinate as input and outputs a scalar or vector value. We coin such representation neural fields. Neural field can circumvent the common challenges of meshes and voxels because it doesn’t explicitly discretize the space and can be stored compactly. Moreover, it has the unique advantage of being easy to optimize in deep-learning frameworks, which makes them suitable for data-driven methods. This thesis demonstrates how to build a geometry processing pipeline using neural fields. Such a pipeline can improve shape creation efficiency, democratize the 3D assets creation process, and revolutionize the digital shape creation paradigm.","abstract_html":"Geometry processing consists of algorithms for shape creation, manipulation, and analysis. These algorithms are cornerstones for the creation of almost every digital shapes. These shapes are consumed in our everyday lives, from digital contents to manufactured objects. These algorithms are indispensable parts of our every life. Traditionally, geometry processing algorithms are usually done with shape represented in explicit representations such as meshes, voxels, and their variants. These shape representations are easy to interpret by human, but they are difficult to be handled by automatic algorithms. For example, voxels can take up a lots of memory and meshes might need careful handle of the discretization quality during the processing. These challenges make development of geometry processing algorithms difficult and inefficient. In this thesis, we propose to use an alternative shape representation for the geometry processing pipeline. Specifically, each shape is represented by a neural network that takes a spatial coordinate as input and outputs a scalar or vector value. We coin such representation neural fields. Neural field can circumvent the common challenges of meshes and voxels because it doesn’t explicitly discretize the space and can be stored compactly. Moreover, it has the unique advantage of being easy to optimize in deep-learning frameworks, which makes them suitable for data-driven methods. This thesis demonstrates how to build a geometry processing pipeline using neural fields. Such a pipeline can improve shape creation efficiency, democratize the 3D assets creation process, and revolutionize the digital shape creation paradigm.","abstract_has_math":false,"creators":["Yang, Guandao"],"institution":"Cornell University","degree_name":"Ph. D., Computer Science","degree_level":"Doctor of Philosophy","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":["Hariharan, Bharath","De Sa, Christopher","Snavely, Keith"],"year":2023,"date_issued":"2023-08","date_published":"2023-08","updated_at":"2026-07-24T01:48:56Z","subjects":["Artificial Intelligence","Computer Graphics","Computer Vision","Geometry Processing","Machine Learning","Shape Analysis"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/nxrc-ps68"],"render_values":[{"text":"https://doi.org/10.7298/nxrc-ps68","href":"https://doi.org/10.7298/nxrc-ps68","code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 13719","ProQuest Publication ID: 30526098"],"render_values":[{"text":"ProQuest Submission ID: 13719","href":null,"code":true},{"text":"ProQuest Publication ID: 30526098","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/1813/114812","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Hariharan, Bharath","De Sa, Christopher","Snavely, Keith"]},{"key":"dc:creator","label":"Author","values":["Yang, Guandao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-04-05T18:48:38Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-08"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctor of Philosophy"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D., Computer Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Cornell University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence","Computer Graphics","Computer Vision","Geometry Processing","Machine Learning","Shape Analysis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/nxrc-ps68"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 13719","ProQuest Publication ID: 30526098"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/114812"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["196 pages"]},{"key":"dc:description.abstract","label":"Abstract","values":["Geometry processing consists of algorithms for shape creation, manipulation, and analysis. These algorithms are cornerstones for the creation of almost every digital shapes. These shapes are consumed in our everyday lives, from digital contents to manufactured objects. These algorithms are indispensable parts of our every life. Traditionally, geometry processing algorithms are usually done with shape represented in explicit representations such as meshes, voxels, and their variants. These shape representations are easy to interpret by human, but they are difficult to be handled by automatic algorithms. For example, voxels can take up a lots of memory and meshes might need careful handle of the discretization quality during the processing. These challenges make development of geometry processing algorithms difficult and inefficient. In this thesis, we propose to use an alternative shape representation for the geometry processing pipeline. Specifically, each shape is represented by a neural network that takes a spatial coordinate as input and outputs a scalar or vector value. We coin such representation neural fields. Neural field can circumvent the common challenges of meshes and voxels because it doesn’t explicitly discretize the space and can be stored compactly. Moreover, it has the unique advantage of being easy to optimize in deep-learning frameworks, which makes them suitable for data-driven methods. This thesis demonstrates how to build a geometry processing pipeline using neural fields. Such a pipeline can improve shape creation efficiency, democratize the 3D assets creation process, and revolutionize the digital shape creation paradigm."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Geometry Processing with Neural Fields"]}]}],"canonical_facts":{"dc:contributor.committeemember":["Hariharan, Bharath","De Sa, Christopher","Snavely, Keith"],"dc:creator":["Yang, Guandao"],"dc:date.accessioned":["2024-04-05T18:48:38Z"],"dc:date.issued":["2023-08"],"dc:description":["196 pages"],"dc:description.abstract":["Geometry processing consists of algorithms for shape creation, manipulation, and analysis. These algorithms are cornerstones for the creation of almost every digital shapes. These shapes are consumed in our everyday lives, from digital contents to manufactured objects. These algorithms are indispensable parts of our every life. Traditionally, geometry processing algorithms are usually done with shape represented in explicit representations such as meshes, voxels, and their variants. These shape representations are easy to interpret by human, but they are difficult to be handled by automatic algorithms. For example, voxels can take up a lots of memory and meshes might need careful handle of the discretization quality during the processing. These challenges make development of geometry processing algorithms difficult and inefficient. In this thesis, we propose to use an alternative shape representation for the geometry processing pipeline. Specifically, each shape is represented by a neural network that takes a spatial coordinate as input and outputs a scalar or vector value. We coin such representation neural fields. Neural field can circumvent the common challenges of meshes and voxels because it doesn’t explicitly discretize the space and can be stored compactly. Moreover, it has the unique advantage of being easy to optimize in deep-learning frameworks, which makes them suitable for data-driven methods. This thesis demonstrates how to build a geometry processing pipeline using neural fields. Such a pipeline can improve shape creation efficiency, democratize the 3D assets creation process, and revolutionize the digital shape creation paradigm."],"dc:format.mimetype":["application/pdf"],"dc:identifier.doi":["https://doi.org/10.7298/nxrc-ps68"],"dc:identifier.other":["ProQuest Submission ID: 13719","ProQuest Publication ID: 30526098"],"dc:identifier.uri":["https://hdl.handle.net/1813/114812"],"dc:language.iso":["en"],"dc:subject":["Artificial Intelligence","Computer Graphics","Computer Vision","Geometry Processing","Machine Learning","Shape Analysis"],"dc:title":["Geometry Processing with Neural Fields"],"dc:type":["dissertation or thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Doctor of Philosophy"],"thesis:degree_name":["Ph. D., Computer Science"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-07-24T01:48:56Z"}