提出新型压缩分层标记器，让自回归图像生成更快更准。
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
- 用深度压缩混合标记器实现32倍空间压缩，保留高质量重建能力。
- 在MJHQ-30K上达到5.49的gFID，GenEval得分0.69，性能领先。
- 相比主流模型，吞吐量提升1.5至7.9倍，延迟降低2.0至3.5倍。
我们提出DC-AR，一种新型的掩码自回归（masked AR）文本到图像生成框架，可在保持卓越计算效率的同时实现优异的图像生成质量。由于标记器的局限性，以往的掩码自回归模型在质量或效率上均落后于扩散模型。为此，我们引入了深度压缩混合标记器（DC-HT），在实现32倍空间压缩比的同时，仍能保持高重建保真度和跨分辨率泛化能力。基于此，我们扩展了MaskGIT，构建了一种新的混合掩码自回归图像生成框架：先通过离散标记生成结构元素，再利用残差标记进行精细化修正。DC-AR在MJHQ-30K数据集上取得5.49的gFID，在GenEval上获得0.69的整体评分，同时相较先前领先的扩散模型和自回归模型，具有1.5至7.9倍更高的吞吐量和2.0至3.5倍更低的延迟。
原文摘要 · Abstract (English)
We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models have lagged behind diffusion models in terms of quality or efficiency. We overcome this limitation by introducing DC-HT - a deep compression hybrid tokenizer for AR models that achieves a 32x spatial compression ratio while maintaining high reconstruction fidelity and cross-resolution generalization ability. Building upon DC-HT, we extend MaskGIT and create a new hybrid masked autoregressive image generation framework that first produces the structural elements through discrete tokens and then applies refinements via residual tokens. DC-AR achieves state-of-the-art results with a gFID of 5.49 on MJHQ-30K and an overall score of 0.69 on GenEval, while offering 1.5-7.9x higher throughput and 2.0-3.5x lower latency compared to prior leading diffusion and autoregressive models.
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。