{"id":{"repo_id":"clemson","oai_identifier":"oai:open.clemson.edu:all_theses-5709"},"canonical_url":"https://search.ndltd.org/etd/clemson/oai:open.clemson.edu:all_theses-5709","repository":{"repo_id":"clemson","name":"Clemson University","base_url":"https://open.clemson.edu/do/oai/"},"display":{"title":"Editable 4D Gaussian Splatting: Scalable and Consistent Video Editing via UV-Texture Decomposition","abstract":"Dynamic 3D videos are now widely used in VR, AR, and telepresence, where users often want to change the style or appearance of objects such as clothing over a whole sequence. However, editing such dynamic 3D content is still hard, because appearance, geometry, and motion are tightly coupled, so even a simple color change must stay consistent in all views and at all time steps. Existing editing methods based on 4D Gaussian Splatting often work in a frame-by-frame way, which is slow and makes it difficult to keep temporal and multi-view consistency. This thesis proposes Editable-4DGS, a representation-centric framework that separates appearance from motion on top of 4DGS. We first reconstruct a 4DGS scene and learn a canonical UV texture that stores the appearance of the 4D geometry. Then we use optical-flow–conditioned Gaussian flow to track each Gaussian over time and to compute a UV trajectory for each frame, while the canonical texture itself stays fixed. On top of this, per-Gaussian semantic features allow us to select meaningful regions, such as a shirt, and perform semantic-aware retexturing directly in UV space. In this way, editing a dynamic scene is reduced to changing a single canonical texture, and the system automatically propagates this change to all frames. Experiments on DyNeRF and Tensor4D datasets show that Editable-4DGS produces more temporally and multi-view consistent retexturing than the baseline, and also provides better semantic control.","abstract_html":"Dynamic 3D videos are now widely used in VR, AR, and telepresence, where users often want to change the style or appearance of objects such as clothing over a whole sequence. However, editing such dynamic 3D content is still hard, because appearance, geometry, and motion are tightly coupled, so even a simple color change must stay consistent in all views and at all time steps. Existing editing methods based on 4D Gaussian Splatting often work in a frame-by-frame way, which is slow and makes it difficult to keep temporal and multi-view consistency. This thesis proposes Editable-4DGS, a representation-centric framework that separates appearance from motion on top of 4DGS. We first reconstruct a 4DGS scene and learn a canonical UV texture that stores the appearance of the 4D geometry. Then we use optical-flow–conditioned Gaussian flow to track each Gaussian over time and to compute a UV trajectory for each frame, while the canonical texture itself stays fixed. On top of this, per-Gaussian semantic features allow us to select meaningful regions, such as a shirt, and perform semantic-aware retexturing directly in UV space. In this way, editing a dynamic scene is reduced to changing a single canonical texture, and the system automatically propagates this change to all frames. Experiments on DyNeRF and Tensor4D datasets show that Editable-4DGS produces more temporally and multi-view consistent retexturing than the baseline, and also provides better semantic control.","abstract_has_math":false,"creators":["Lyu, Shuai"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Lan Zhang","Tao Wei","Luyang Zhao"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:33:56Z","subjects":["4D Gaussian Splatting","dynamic scene editing","UV texture mapping","retexturing","3D video editing","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://open.clemson.edu/all_theses/4663","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://open.clemson.edu/all_theses/4663","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.clemson.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopen.clemson.edu%3Aall_theses-5709","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lan Zhang","Tao Wei","Luyang Zhao"]},{"key":"dc:creator","label":"Author","values":["Lyu, Shuai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-11-28T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["4D Gaussian Splatting","dynamic scene editing","UV texture mapping","retexturing","3D video editing","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://open.clemson.edu/all_theses/4663"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Dynamic 3D videos are now widely used in VR, AR, and telepresence, where users often want to change the style or appearance of objects such as clothing over a whole sequence. However, editing such dynamic 3D content is still hard, because appearance, geometry, and motion are tightly coupled, so even a simple color change must stay consistent in all views and at all time steps. Existing editing methods based on 4D Gaussian Splatting often work in a frame-by-frame way, which is slow and makes it difficult to keep temporal and multi-view consistency. This thesis proposes Editable-4DGS, a representation-centric framework that separates appearance from motion on top of 4DGS. We first reconstruct a 4DGS scene and learn a canonical UV texture that stores the appearance of the 4D geometry. Then we use optical-flow–conditioned Gaussian flow to track each Gaussian over time and to compute a UV trajectory for each frame, while the canonical texture itself stays fixed. On top of this, per-Gaussian semantic features allow us to select meaningful regions, such as a shirt, and perform semantic-aware retexturing directly in UV space. In this way, editing a dynamic scene is reduced to changing a single canonical texture, and the system automatically propagates this change to all frames. Experiments on DyNeRF and Tensor4D datasets show that Editable-4DGS produces more temporally and multi-view consistent retexturing than the baseline, and also provides better semantic control."]},{"key":"dc:title","label":"Title","values":["Editable 4D Gaussian Splatting: Scalable and Consistent Video Editing via UV-Texture Decomposition"]}]}],"canonical_facts":{"dc:contributor":["Lan Zhang","Tao Wei","Luyang Zhao"],"dc:creator":["Lyu, Shuai"],"dc:date.available":["2025-11-28T08:00:00Z"],"dc:date.created":["2025-12-01T08:00:00Z"],"dc:description.abstract":["Dynamic 3D videos are now widely used in VR, AR, and telepresence, where users often want to change the style or appearance of objects such as clothing over a whole sequence. However, editing such dynamic 3D content is still hard, because appearance, geometry, and motion are tightly coupled, so even a simple color change must stay consistent in all views and at all time steps. Existing editing methods based on 4D Gaussian Splatting often work in a frame-by-frame way, which is slow and makes it difficult to keep temporal and multi-view consistency. This thesis proposes Editable-4DGS, a representation-centric framework that separates appearance from motion on top of 4DGS. We first reconstruct a 4DGS scene and learn a canonical UV texture that stores the appearance of the 4D geometry. Then we use optical-flow–conditioned Gaussian flow to track each Gaussian over time and to compute a UV trajectory for each frame, while the canonical texture itself stays fixed. On top of this, per-Gaussian semantic features allow us to select meaningful regions, such as a shirt, and perform semantic-aware retexturing directly in UV space. In this way, editing a dynamic scene is reduced to changing a single canonical texture, and the system automatically propagates this change to all frames. Experiments on DyNeRF and Tensor4D datasets show that Editable-4DGS produces more temporally and multi-view consistent retexturing than the baseline, and also provides better semantic control."],"dc:identifier":["https://open.clemson.edu/all_theses/4663"],"dc:subject":["4D Gaussian Splatting","dynamic scene editing","UV texture mapping","retexturing","3D video editing","Electrical and Computer Engineering"],"dc:title":["Editable 4D Gaussian Splatting: Scalable and Consistent Video Editing via UV-Texture Decomposition"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T07:33:56Z"}