3 papers
cs.CV2026
DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image Generation
Xin Jiang, Jingwen Chen, Yehao Li +5
Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images.…
cs.CV2025
Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On
Siqi Wan, Jingwen Chen, Yingwei Pan +2
Diffusion models have shown preliminary success in virtual try-on (VTON) task. The typical dual-branch architecture comprises two UNets for implicit garment deformation and synthes…
cs.CV2024
Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning
Jianjie Luo, Jingwen Chen, Yehao Li +4
Recently, zero-shot image captioning has gained increasing attention, where only text data is available for training. The remarkable progress in text-to-image diffusion model prese…