MaskBit: Embedding-Free Image Generation via Bit Tokens

MCML Authors

Mark Weber

→ Group Daniel Cremers
 Computer Vision & Artificial Intelligence

Daniel Cremers

Prof. Dr.

Director

Computer Vision & Artificial Intelligence

Abstract

Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subsequent Transformer model for image generation within latent space - these frameworks offer promising avenues for image synthesis. In this study, we present two primary contributions: Firstly, an empirical and systematic examination of VQGANs, leading to a modernized VQGAN. Secondly, a novel embedding-free generation network operating directly on bit tokens - a binary quantized representation of tokens with rich semantics. The first contribution furnishes a transparent, reproducible, and high-performing VQGAN model, enhancing accessibility and matching the performance of current state-of-the-art methods while revealing previously undisclosed details. The second contribution demonstrates that embedding-free image generation using bit tokens achieves a new state-of-the-art FID of 1.52 on the ImageNet 256x256 benchmark, with a compact generator model of mere 305M parameters.

article

---

Transactions on Machine Learning Research

Dec. 2024. Certifications: Reproducibility, Featured.

---

Authors

M. Weber • L. Yu • Q. Yu • X. Deng • X. Shen • D. Cremers • L.-C. Chen

---

Links

URL

---

Research Area

 B1 | Computer Vision