A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

TL;DR

This paper introduces the DnD-Transformer, a 2D autoregressive model that enhances image generation quality and demonstrates emergent vision-language understanding by generating images with text and graphics.

Contribution

The novel 2D autoregression architecture improves image quality and enables self-supervised vision-language capabilities in autoregressive models.

Findings

Higher quality images with same model size and sequence length

Ability to generate images with rich text and graphical elements

Demonstrates vision-language understanding without multimodal training

Abstract

This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts more codes for an image by introducing a new autoregression direction, \textit{model depth}, along with the sequence length direction. Compared to traditional 1D autoregression and previous work utilizing similar 2D image decomposition such as RQ-Transformer, the DnD-Transformer is an end-to-end model that can generate higher quality images with the same backbone model size and sequence length, opening a new optimization perspective for autoregressive image generation. Furthermore, our experiments reveal that the DnD-Transformer's potential extends beyond generating natural images. It can even generate images with rich text and graphical elements in a self-supervised manner, demonstrating an understanding of these combined modalities. This has not been previously demonstrated for popular vision generative models such as diffusion models, showing a spark of vision-language intelligence when trained solely on images. Code, datasets and models are open at https://github.com/chenllliang/DnD-Transformer.