Controllable Anime Image Editing Based on the Probability of Attribute Tags

Simple item page
dc.contributor.authorSong, Zhenghaoen_US
dc.contributor.authorMo, Haoranen_US
dc.contributor.authorGao, Chengyingen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:09:18Z
dc.date.available2024-10-13T18:09:18Z
dc.date.issued2024
dc.description.abstractEditing anime images via probabilities of attribute tags allows controlling the degree of the manipulation in an intuitive and convenient manner. Existing methods fall short in the progressive modification and preservation of unintended regions in the input image. We propose a controllable anime image editing framework based on adjusting the tag probabilities, in which a probability encoding network (PEN) is developed to encode the probabilities into features that capture continuous characteristic of the probabilities. Thus, the encoded features are able to direct the generative process of a pre-trained diffusion model and facilitate the linear manipulation.We also introduce a local editing module that automatically identifies the intended regions and constrains the edits to be applied to those regions only, which preserves the others unchanged. Comprehensive comparisons with existing methods indicate the effectiveness of our framework in both one-shot and linear editing modes. Results in additional applications further demonstrate the generalization ability of our approach.en_US
dc.description.number7
dc.description.sectionheadersImage Synthesis
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15245
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15245
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15245
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Image processing
dc.subjectComputing methodologies → Image processing
dc.titleControllable Anime Image Editing Based on the Probability of Attribute Tagsen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
cgf15245.pdf
Size:
10.03 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1148_supplemental_material.pdf
Size:
7.27 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1148_video.mp4
Size:
5.43 MB
Format:
Video MP4
Download
Collections
43-Issue 7