用比特掩码生成图像，突破离散生成性能瓶颈
Autoregressive Image Generation with Masked Bit Modeling
- 通过逐位建模预测离散令牌，支持任意码本大小
- ImageNet-256上达gFID 0.99，超越主流连续与离散方法
- 训练快、采样成本低，适合大规模图像生成应用
本文挑战视觉生成中连续方法的主导地位。系统研究了离散与连续方法之间的性能差距，发现差异主要源于潜在空间中分配的总比特数（即压缩比）。我们证明，增大码本规模可有效弥合这一差距，使离散分词器达到甚至超越连续方法。然而，现有离散生成方法在扩大码本时面临性能下降或训练成本过高的问题。为此，我们提出掩码比特自回归建模（BAR），一种支持任意码本大小的可扩展框架。通过在自回归Transformer上引入掩码比特建模头，BAR逐步生成令牌的比特表示。BAR在ImageNet-256上实现0.99的gFID新纪录，优于所有现有连续与离散方法，同时显著降低采样开销并比先前连续方法收敛更快。
原文摘要 · Abstract (English)
This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically inferior, we demonstrate that the disparity arises primarily from the total number of bits allocated in the latent space (i.e., the compression ratio). We show that scaling up the codebook size effectively bridges this gap, allowing discrete tokenizers to match or surpass their continuous counterparts. However, existing discrete generation methods struggle to capitalize on this insight, suffering from performance degradation or prohibitive training costs with scaled codebook. To address this, we propose masked Bit AutoRegressive modeling (BAR), a scalable framework that supports arbitrary codebook sizes. By equipping an autoregressive transformer with a masked bit modeling head, BAR predicts discrete tokens through progressively generating their constituent bits. BAR achieves a new state-of-the-art gFID of 0.99 on ImageNet-256, outperforming leading methods across both continuous and discrete paradigms, while significantly reducing sampling costs and converging faster than prior continuous approaches. Project page is available at https://bar-gen.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。