147897 20250109162738.0 doi 10.1145/3641519.3657444 sideral 141304 ART-2024-141304 eng Guerrero-Viu, Julia Universidad de Zaragoza (orcid)0000-0002-2077-683X TexSliders: Diffusion-Based Texture Editing in CLIP Space 2024 Generative models have enabled intuitive image creation and manipulation using natural language. In particular, diffusion models have recently shown remarkable results for natural image editing. In this work, we propose to apply diffusion techniques to edit textures, a specific class of images that are an essential part of 3D content creation pipelines. We analyze existing editing methods and show that they are not directly applicable to textures, since their common underlying approach, manipulating attention maps, is unsuitable for the texture domain. To address this, we propose a novel approach that instead manipulates CLIP image embeddings to condition the diffusion generation. We define editing directions using simple text prompts (e.g., “aged wood” to “new wood”) and map these to CLIP image embedding space using a texture prior, with a sampling-based approach that gives us identity-preserving directions in CLIP space. To further improve identity preservation, we project these directions to a CLIP subspace that minimizes identity variations resulting from entangled texture attributes. Our editing pipeline facilitates the creation of arbitrary sliders using natural language prompts only, with no ground-truth annotated data necessary. info:eu-repo/grantAgreement/EC/H2020/956585/EU/Predictive Rendering In Manufacture and Engineering/PRIME This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 956585-PRIME info:eu-repo/grantAgreement/ES/MCIU/FPU20-02340 info:eu-repo/grantAgreement/ES/MICINN/PID2022-141766OB-I00 info:eu-repo/semantics/closedAccess All rights reserved http://www.europeana.eu/rights/rr-f/ info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Hasan, Milos Roullier, Arthur Harikumar, Midhun Hu, Yiwei Guerrero, Paul Gutiérrez, Diego Universidad de Zaragoza (orcid)0000-0002-7503-7022 Masia, Belen Universidad de Zaragoza (orcid)0000-0003-0060-7278 Deschaintre, Valentin 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. (2024), 7 [11 pp.] Proc. ACM SIGGRAPH Proceedings of ACM SIGGRAPH 2376-1180 970752 http://zaguan.unizar.es/record/147897/files/texto_completo.pdf Versión publicada 2512023 http://zaguan.unizar.es/record/147897/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:147897 articulos driver 2025-01-09-14:41:27 ARTICLE