Directional Texture Editing for 3D Models

Simple item page
dc.contributor.authorLiu, Shengqien_US
dc.contributor.authorChen, Zhuoen_US
dc.contributor.authorGao, Jingnanen_US
dc.contributor.authorYan, Yichaoen_US
dc.contributor.authorZhu, Wenhanen_US
dc.contributor.authorLyu, Jiangjingen_US
dc.contributor.authorYang, Xiaokangen_US
dc.contributor.editorAlliez, Pierreen_US
dc.contributor.editorWimmer, Michaelen_US
dc.date.accessioned2024-12-19T11:15:20Z
dc.date.available2024-12-19T11:15:20Z
dc.date.issued2024
dc.description.abstractTexture editing is a crucial task in 3D modelling that allows users to automatically manipulate the surface materials of 3D models. However, the inherent complexity of 3D models and the ambiguous text description lead to the challenge of this task. To tackle this challenge, we propose ITEM3D, a exture diting odel designed for automatic object editing according to the text nstructions. Leveraging the diffusion models and the differentiable rendering, ITEM3D takes the rendered images as the bridge between text and 3D representation and further optimizes the disentangled texture and environment map. Previous methods adopted the absolute editing direction, namely score distillation sampling (SDS) as the optimization objective, which unfortunately results in noisy appearances and text inconsistencies. To solve the problem caused by the ambiguous text, we introduce a relative editing direction, an optimization objective defined by the noise difference between the source and target texts, to release the semantic ambiguity between the texts and images. Additionally, we gradually adjust the direction during optimization to further address the unexpected deviation in the texture domain. Qualitative and quantitative experiments show that our ITEM3D outperforms the state‐of‐the‐art methods on various 3D objects. We also perform text‐guided relighting to show explicit control over lighting. Our project page: .en_US
dc.description.number6
dc.description.sectionheadersORIGINAL ARTICLES
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15196
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15196
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15196
dc.publisher© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectimage and video processing
dc.subjectimage/video editing
dc.subjectrendering
dc.subjecttexture synthesis
dc.titleDirectional Texture Editing for 3D Modelsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
09_cgf15196.pdf
Size:
8.53 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 6