{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/151350"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/151350","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Unsupervised Compositional Image Decompositionwith Diffusion Models","abstract":"Our visual understanding of the world is factorized and compositional. With just a single observation, we can ascertain both global and local attributes in a scene, such as lighting, weather, and underlying objects. These attributes are highly compositional and can be combined in various ways to create new representations of the world. This paper introduces Decomp Diffusion, an unsupervised method for decomposing images into a set of underlying compositional factors, each represented by a different diffusion model. We demonstrate how each decomposed diffusion model captures a different factor of the scene, ranging from global scene descriptors, (e.g. shadows, foreground, or facial expression) to local scene descriptors (e.g. constituent objects). Furthermore, we show how these inferred factors can be flexibly composed and recombined both within and across different image datasets.","abstract_html":"Our visual understanding of the world is factorized and compositional. With just a single observation, we can ascertain both global and local attributes in a scene, such as lighting, weather, and underlying objects. These attributes are highly compositional and can be combined in various ways to create new representations of the world. This paper introduces Decomp Diffusion, an unsupervised method for decomposing images into a set of underlying compositional factors, each represented by a different diffusion model. We demonstrate how each decomposed diffusion model captures a different factor of the scene, ranging from global scene descriptors, (e.g. shadows, foreground, or facial expression) to local scene descriptors (e.g. constituent objects). Furthermore, we show how these inferred factors can be flexibly composed and recombined both within and across different image datasets.","abstract_has_math":false,"creators":["Su, Jocelin"],"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":["Tenenbaum, Joshua B."],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06","date_published":"2023-06","updated_at":"2026-07-22T22:21:59Z","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/1721.1/151350","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Tenenbaum, Joshua B."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Su, Jocelin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-07-31T19:33:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-07-31T19:33:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06"]},{"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/1721.1/151350"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Our visual understanding of the world is factorized and compositional. With just a single observation, we can ascertain both global and local attributes in a scene, such as lighting, weather, and underlying objects. These attributes are highly compositional and can be combined in various ways to create new representations of the world. This paper introduces Decomp Diffusion, an unsupervised method for decomposing images into a set of underlying compositional factors, each represented by a different diffusion model. We demonstrate how each decomposed diffusion model captures a different factor of the scene, ranging from global scene descriptors, (e.g. shadows, foreground, or facial expression) to local scene descriptors (e.g. constituent objects). Furthermore, we show how these inferred factors can be flexibly composed and recombined both within and across different image datasets."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Unsupervised Compositional Image Decompositionwith Diffusion Models"]}]}],"canonical_facts":{"dc:contributor.advisor":["Tenenbaum, Joshua B."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Su, Jocelin"],"dc:date.accessioned":["2023-07-31T19:33:22Z"],"dc:date.available":["2023-07-31T19:33:22Z"],"dc:date.issued":["2023-06"],"dc:description.abstract":["Our visual understanding of the world is factorized and compositional. With just a single observation, we can ascertain both global and local attributes in a scene, such as lighting, weather, and underlying objects. These attributes are highly compositional and can be combined in various ways to create new representations of the world. This paper introduces Decomp Diffusion, an unsupervised method for decomposing images into a set of underlying compositional factors, each represented by a different diffusion model. We demonstrate how each decomposed diffusion model captures a different factor of the scene, ranging from global scene descriptors, (e.g. shadows, foreground, or facial expression) to local scene descriptors (e.g. constituent objects). Furthermore, we show how these inferred factors can be flexibly composed and recombined both within and across different image datasets."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/151350"],"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":["Unsupervised Compositional Image Decompositionwith Diffusion Models"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:59Z"}