LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929655478484992 |
|---|---|
| author | Kang, Kyoungkook Sim, Gyujin Kim, Geonung Kim, Donguk Nam, Seungho Cho, Sunghyun |
| author_facet | Kang, Kyoungkook Sim, Gyujin Kim, Geonung Kim, Donguk Nam, Seungho Cho, Sunghyun |
| contents | Layers have become indispensable tools for professional artists, allowing them to build a hierarchical structure that enables independent control over individual visual elements. In this paper, we propose LayeringDiff, a novel pipeline for the synthesis of layered images, which begins by generating a composite image using an off-the-shelf image generative model, followed by disassembling the image into its constituent foreground and background layers. By extracting layers from a composite image, rather than generating them from scratch, LayeringDiff bypasses the need for large-scale training to develop generative capabilities for individual layers. Furthermore, by utilizing a pretrained off-the-shelf generative model, our method can produce diverse contents and object scales in synthesized layers. For effective layer decomposition, we adapt a large-scale pretrained generative prior to estimate foreground and background layers. We also propose high-frequency alignment modules to refine the fine-details of the estimated layers. Our comprehensive experiments demonstrate that our approach effectively synthesizes layered images and supports various practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge Kang, Kyoungkook Sim, Gyujin Kim, Geonung Kim, Donguk Nam, Seungho Cho, Sunghyun Computer Vision and Pattern Recognition Layers have become indispensable tools for professional artists, allowing them to build a hierarchical structure that enables independent control over individual visual elements. In this paper, we propose LayeringDiff, a novel pipeline for the synthesis of layered images, which begins by generating a composite image using an off-the-shelf image generative model, followed by disassembling the image into its constituent foreground and background layers. By extracting layers from a composite image, rather than generating them from scratch, LayeringDiff bypasses the need for large-scale training to develop generative capabilities for individual layers. Furthermore, by utilizing a pretrained off-the-shelf generative model, our method can produce diverse contents and object scales in synthesized layers. For effective layer decomposition, we adapt a large-scale pretrained generative prior to estimate foreground and background layers. We also propose high-frequency alignment modules to refine the fine-details of the estimated layers. Our comprehensive experiments demonstrate that our approach effectively synthesizes layered images and supports various practical applications. |
| title | LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01197 |