High-fidelity Person-centric Subject-to-Image Synthesis

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 7675 - 7684
• Main Authors: Wang, Yibin, Zhang, Weizhong, Zheng, Jianwei, Jin, Cheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: Collaboration; Diffusion; Image synthesis; Noise; Pipelines; Predictive models; Semantics; Subject-to-Image Synthesis; Text-to-Image Synthesis; Training

Current subject-driven image generation methods en-counter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which involves an irreconcilable training imbalance. Precisely,...