Saved in:
Bibliographic Details
Main Authors: Pu, Yifan, Zhao, Yiming, Tang, Zhicong, Yin, Ruihong, Ye, Haoxing, Yuan, Yuhui, Chen, Dong, Bao, Jianmin, Zhang, Sirui, Wang, Yanbin, Liang, Lin, Wang, Lijuan, Li, Ji, Li, Xiu, Lian, Zhouhui, Huang, Gao, Guo, Baining
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.18364
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913706744479744
author Pu, Yifan
Zhao, Yiming
Tang, Zhicong
Yin, Ruihong
Ye, Haoxing
Yuan, Yuhui
Chen, Dong
Bao, Jianmin
Zhang, Sirui
Wang, Yanbin
Liang, Lin
Wang, Lijuan
Li, Ji
Li, Xiu
Lian, Zhouhui
Huang, Gao
Guo, Baining
author_facet Pu, Yifan
Zhao, Yiming
Tang, Zhicong
Yin, Ruihong
Ye, Haoxing
Yuan, Yuhui
Chen, Dong
Bao, Jianmin
Zhang, Sirui
Wang, Yanbin
Liang, Lin
Wang, Lijuan
Li, Ji
Li, Xiu
Lian, Zhouhui
Huang, Gao
Guo, Baining
contents Multi-layer image generation is a fundamental task that enables users to isolate, select, and edit specific image layers, thereby revolutionizing interactions with generative models. In this paper, we introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images based on a global text prompt and an anonymous region layout. Inspired by Schema theory suggests that knowledge is organized in frameworks (schemas) that enable people to interpret and learn from new information by linking it to prior knowledge.}, this anonymous region layout allows the generative model to autonomously determine which set of visual tokens should align with which text tokens, which is in contrast to the previously dominant semantic layout for the image generation task. In addition, the layer-wise region crop mechanism, which only selects the visual tokens belonging to each anonymous region, significantly reduces attention computation costs and enables the efficient generation of images with numerous distinct layers (e.g., 50+). When compared to the full attention approach, our method is over 12 times faster and exhibits fewer layer conflicts. Furthermore, we propose a high-quality multi-layer transparent image autoencoder that supports the direct encoding and decoding of the transparency of variable multi-layer images in a joint manner. By enabling precise control and scalable layer generation, ART establishes a new paradigm for interactive content creation.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18364
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
Pu, Yifan
Zhao, Yiming
Tang, Zhicong
Yin, Ruihong
Ye, Haoxing
Yuan, Yuhui
Chen, Dong
Bao, Jianmin
Zhang, Sirui
Wang, Yanbin
Liang, Lin
Wang, Lijuan
Li, Ji
Li, Xiu
Lian, Zhouhui
Huang, Gao
Guo, Baining
Computer Vision and Pattern Recognition
Multi-layer image generation is a fundamental task that enables users to isolate, select, and edit specific image layers, thereby revolutionizing interactions with generative models. In this paper, we introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images based on a global text prompt and an anonymous region layout. Inspired by Schema theory suggests that knowledge is organized in frameworks (schemas) that enable people to interpret and learn from new information by linking it to prior knowledge.}, this anonymous region layout allows the generative model to autonomously determine which set of visual tokens should align with which text tokens, which is in contrast to the previously dominant semantic layout for the image generation task. In addition, the layer-wise region crop mechanism, which only selects the visual tokens belonging to each anonymous region, significantly reduces attention computation costs and enables the efficient generation of images with numerous distinct layers (e.g., 50+). When compared to the full attention approach, our method is over 12 times faster and exhibits fewer layer conflicts. Furthermore, we propose a high-quality multi-layer transparent image autoencoder that supports the direct encoding and decoding of the transparency of variable multi-layer images in a joint manner. By enabling precise control and scalable layer generation, ART establishes a new paradigm for interactive content creation.
title ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.18364