3 papers
cs.CV2024
RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Prediction
Xiaoping Wu, Jie Hu, Xiaoming Wei
Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which signifi…
cs.CV2024
CharGen: High Accurate Character-Level Visual Text Generation Model with MultiModal Encoder
Lichen Ma, Tiezhu Yue, Pei Fu +4
Recently, significant advancements have been made in diffusion-based visual text generation models. Although the effectiveness of these methods in visual text rendering is rapidly…
cs.CV2024
ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
Chen Duan, Pei Fu, Shan Guo +2
In recent years, text-image joint pre-training techniques have shown promising results in various tasks. However, in Optical Character Recognition (OCR) tasks, aligning text instan…