2025/12/18 by Rao, Qihang, Zhang, Borui, Zheng, Wenzhao +2
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image Enhancement Techniques #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2512.16910
openalex publication_date 2025/12/18 · openalex created_date 2025/12/21 · openalex updated_date 2026/07/28
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in lower-dimensional spaces, thereby improving computational efficiency and reducing complexity. Discrete tokenizers naturally align with the autoregressive paradigm but still lag behind continuous ones, limiting their adoption in multimodal systems. To address this, we propose SFTok, a discrete tokenizer that incorporates a multi-step iterative mechanism for precise reconstruction. By integrating self-forcing guided visual reconstruction and debias-and-fitting training strategy, SFTok resolves the training-inference inconsistency in multi-step process, significantly enhancing image reconstruction quality. At a high compression rate of only 64 tokens per image, SFTok achieves state-of-the-art reconstruction quality on ImageNet (rFID = 1.21) and demonstrates exceptional performance in class-to-image generation tasks (gFID = 2.29).