TiTok: A Transformer-based 1D Tokenization Approach for Image Generation
Generative Models
Computer Vision
Transformers
Read transcript · Original paper
AI-generated voices discussing a paper selected by Arjun Srivastava.
About this paper
TiTok introduces a novel 1D tokenization method for image generation, enabling the representation of images with significantly fewer tokens while maintaining or surpassing the performance of existing 2D grid-based methods. The approach leverages a Vision Transformer architecture, two-stage training with proxy codes, and achieves remarkable speedup in training and inference. The research opens up new possibilities for efficient and high-quality image generation, with implications for various applications in computer vision and beyond.