{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/159088"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/159088","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Realistic Tactile Stylization for Digital Fabrication using Enhanced UV Unwrapping Method","abstract":"While recent advances in Generative AI enable visual stylization of 3D models using image prompts, they typically neglect tactile properties. TactStyle addresses this limitation by enabling creators to enhance 3D models with both visual and tactile properties derived from texture images. Using a fine-tuned image-generation model, TactStyle generates highly accurate heightfields that faithfully replicate the tactile properties of input visual textures and applies them to 3D models. However, applying textures to 3D models presents challenges, such as ensuring even texture resolution, avoiding texture warping, and minimizing visible seams. TactStyle’s current implementation often struggles with significant texture stretching and distortion caused by poor UV mapping, compromising the accurate heightfields and diminishing the tactile fidelity of printed models. Our research systematically evaluates various UV unwrapping methods, including alternative UV projections and an optimization-based neural UV mapping, to improve the realism and accuracy of texture application on 3D models in digital fabrication. Building on these findings, we will release a Blender plugin that integrates the optimal UV unwrapping methods with TactStyle, enabling creators to easily customize their 3D models with accurate tactile properties using only reference texture images. This work enhances the practicality and accessibility of tactile 3D model customization, bridging the gap between visual and tactile design elements.","abstract_html":"While recent advances in Generative AI enable visual stylization of 3D models using image prompts, they typically neglect tactile properties. TactStyle addresses this limitation by enabling creators to enhance 3D models with both visual and tactile properties derived from texture images. Using a fine-tuned image-generation model, TactStyle generates highly accurate heightfields that faithfully replicate the tactile properties of input visual textures and applies them to 3D models. However, applying textures to 3D models presents challenges, such as ensuring even texture resolution, avoiding texture warping, and minimizing visible seams. TactStyle’s current implementation often struggles with significant texture stretching and distortion caused by poor UV mapping, compromising the accurate heightfields and diminishing the tactile fidelity of printed models. Our research systematically evaluates various UV unwrapping methods, including alternative UV projections and an optimization-based neural UV mapping, to improve the realism and accuracy of texture application on 3D models in digital fabrication. Building on these findings, we will release a Blender plugin that integrates the optimal UV unwrapping methods with TactStyle, enabling creators to easily customize their 3D models with accurate tactile properties using only reference texture images. This work enhances the practicality and accessibility of tactile 3D model customization, bridging the gap between visual and tactile design elements.","abstract_has_math":false,"creators":["Wong, Zoe"],"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":["Mueller, Stefanie"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02","date_published":"2025-02","updated_at":"2026-07-22T22:22:23Z","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/1721.1/159088","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mueller, Stefanie"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Wong, Zoe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-14T14:04:42Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-14T14:04:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-02"]},{"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/1721.1/159088"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["While recent advances in Generative AI enable visual stylization of 3D models using image prompts, they typically neglect tactile properties. TactStyle addresses this limitation by enabling creators to enhance 3D models with both visual and tactile properties derived from texture images. Using a fine-tuned image-generation model, TactStyle generates highly accurate heightfields that faithfully replicate the tactile properties of input visual textures and applies them to 3D models. However, applying textures to 3D models presents challenges, such as ensuring even texture resolution, avoiding texture warping, and minimizing visible seams. TactStyle’s current implementation often struggles with significant texture stretching and distortion caused by poor UV mapping, compromising the accurate heightfields and diminishing the tactile fidelity of printed models. Our research systematically evaluates various UV unwrapping methods, including alternative UV projections and an optimization-based neural UV mapping, to improve the realism and accuracy of texture application on 3D models in digital fabrication. Building on these findings, we will release a Blender plugin that integrates the optimal UV unwrapping methods with TactStyle, enabling creators to easily customize their 3D models with accurate tactile properties using only reference texture images. This work enhances the practicality and accessibility of tactile 3D model customization, bridging the gap between visual and tactile design elements."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Realistic Tactile Stylization for Digital Fabrication using Enhanced UV Unwrapping Method"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mueller, Stefanie"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Wong, Zoe"],"dc:date.accessioned":["2025-04-14T14:04:42Z"],"dc:date.available":["2025-04-14T14:04:42Z"],"dc:date.issued":["2025-02"],"dc:description.abstract":["While recent advances in Generative AI enable visual stylization of 3D models using image prompts, they typically neglect tactile properties. TactStyle addresses this limitation by enabling creators to enhance 3D models with both visual and tactile properties derived from texture images. Using a fine-tuned image-generation model, TactStyle generates highly accurate heightfields that faithfully replicate the tactile properties of input visual textures and applies them to 3D models. However, applying textures to 3D models presents challenges, such as ensuring even texture resolution, avoiding texture warping, and minimizing visible seams. TactStyle’s current implementation often struggles with significant texture stretching and distortion caused by poor UV mapping, compromising the accurate heightfields and diminishing the tactile fidelity of printed models. Our research systematically evaluates various UV unwrapping methods, including alternative UV projections and an optimization-based neural UV mapping, to improve the realism and accuracy of texture application on 3D models in digital fabrication. Building on these findings, we will release a Blender plugin that integrates the optimal UV unwrapping methods with TactStyle, enabling creators to easily customize their 3D models with accurate tactile properties using only reference texture images. This work enhances the practicality and accessibility of tactile 3D model customization, bridging the gap between visual and tactile design elements."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/159088"],"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":["Realistic Tactile Stylization for Digital Fabrication using Enhanced UV Unwrapping Method"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:23Z"}