9 papers
Composable Visual Tokenizers with Generator-Free Diagnostics of Learnability
Bingchen Zhao, Qiushan Guo, Ye Wang +3
We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By emp…
DNA: Uncovering Universal Latent Forgery Knowledge
Jingtong Dou, Chuancheng Shi, Yemin Wang +6
As generative AI achieves hyper-realism, superficial artifact detection has become obsolete. While prevailing methods rely on resource-intensive fine-tuning of black-box backbones,…
PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation
Ting Pan, Ye Wang, Peiguang Jing +3
Personalized dual-person portrait customization has considerable potential applications, such as preserving emotional memories and facilitating wedding photography planning. Howeve…
FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
Jiang Lin, Xinyu Chen, Song Wu +7
Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining…
An Overview of the JPEG AI Learning-Based Image Coding Standard
Semih Esenlik, Yaojun Wu, Zhaobin Zhang +5
JPEG AI is an emerging learning-based image coding standard developed by Joint Photographic Experts Group (JPEG). The scope of the JPEG AI is the creation of a practical learning-b…
OmniStyle: Filtering High Quality Style Transfer Data at Scale
Ye Wang, Ruiqi Liu, Jiang Lin +4
In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style c…