{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/156743"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/156743","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Enhancing 3D Scene Graph Generation with Multimodal Embeddings","abstract":"3D Scene Graphs are expressive map representations for scene understanding in robotics and computer vision. Current approaches for automated zero-shot 3D Scene Graph generation rely on spatial ontologies that relate objects with the semantic locations they are found in (e.g., a fork is found in a kitchen). While conferring impressive zero-shot performance, these approaches are conditioned on the existence of disambiguating objects in a scene, the expressiveness of the generated spatial ontologies, and knowing during data collection that a robot needs to observe specific objects in the environment. This thesis proposes a method for zero-shot scene graph generation by leveraging Vision-Language Models (VLMs) to construct a layer of Viewpoints in the scene graph, which allow for after-the-fact open-vocabulary querying over the scene. Methods for utilizing different VLM features are explored, which result in improvement over the ontological approach on region segmentation tasks.","abstract_html":"3D Scene Graphs are expressive map representations for scene understanding in robotics and computer vision. Current approaches for automated zero-shot 3D Scene Graph generation rely on spatial ontologies that relate objects with the semantic locations they are found in (e.g., a fork is found in a kitchen). While conferring impressive zero-shot performance, these approaches are conditioned on the existence of disambiguating objects in a scene, the expressiveness of the generated spatial ontologies, and knowing during data collection that a robot needs to observe specific objects in the environment. This thesis proposes a method for zero-shot scene graph generation by leveraging Vision-Language Models (VLMs) to construct a layer of Viewpoints in the scene graph, which allow for after-the-fact open-vocabulary querying over the scene. Methods for utilizing different VLM features are explored, which result in improvement over the ontological approach on region segmentation tasks.","abstract_has_math":false,"creators":["Morales, Joseph"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Carlone, Luca"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:20:59Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/156743","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Carlone, Luca"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Morales, Joseph"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-16T13:46:25Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-16T13:46:25Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/156743"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["3D Scene Graphs are expressive map representations for scene understanding in robotics and computer vision. Current approaches for automated zero-shot 3D Scene Graph generation rely on spatial ontologies that relate objects with the semantic locations they are found in (e.g., a fork is found in a kitchen). While conferring impressive zero-shot performance, these approaches are conditioned on the existence of disambiguating objects in a scene, the expressiveness of the generated spatial ontologies, and knowing during data collection that a robot needs to observe specific objects in the environment. This thesis proposes a method for zero-shot scene graph generation by leveraging Vision-Language Models (VLMs) to construct a layer of Viewpoints in the scene graph, which allow for after-the-fact open-vocabulary querying over the scene. Methods for utilizing different VLM features are explored, which result in improvement over the ontological approach on region segmentation tasks."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Enhancing 3D Scene Graph Generation with Multimodal Embeddings"]}]}],"canonical_facts":{"dc:contributor.advisor":["Carlone, Luca"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Morales, Joseph"],"dc:date.accessioned":["2024-09-16T13:46:25Z"],"dc:date.available":["2024-09-16T13:46:25Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["3D Scene Graphs are expressive map representations for scene understanding in robotics and computer vision. Current approaches for automated zero-shot 3D Scene Graph generation rely on spatial ontologies that relate objects with the semantic locations they are found in (e.g., a fork is found in a kitchen). While conferring impressive zero-shot performance, these approaches are conditioned on the existence of disambiguating objects in a scene, the expressiveness of the generated spatial ontologies, and knowing during data collection that a robot needs to observe specific objects in the environment. This thesis proposes a method for zero-shot scene graph generation by leveraging Vision-Language Models (VLMs) to construct a layer of Viewpoints in the scene graph, which allow for after-the-fact open-vocabulary querying over the scene. Methods for utilizing different VLM features are explored, which result in improvement over the ontological approach on region segmentation tasks."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/156743"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Enhancing 3D Scene Graph Generation with Multimodal Embeddings"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:20:59Z"}