用离散标记做条件，生成连续图像，提升画质。
Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
- 将离散标记当作条件而非生成目标
- 在ImageNet上实现1.38的gFID，优于现有方法
- 适合关注图像生成质量与推理效率的研究者
大语言模型的发展推动了将图像编码为离散标记并使用自回归框架进行视觉生成的研究。然而，自回归视觉生成模型中的量化过程会引入信息损失，降低图像保真度。为缓解这一限制，近期研究尝试自回归预测连续标记。不同于存在于结构化有界空间的离散标记，连续表示存在于无界高维空间，使密度估计更具挑战性，并增加生成分布外伪影的风险。本文提出DisCon（离散条件化连续自回归模型），重新将离散标记视为条件信号而非生成目标。通过建模在离散标记条件下连续表示的条件概率，DisCon避免了连续标记建模的优化难题，同时规避了量化带来的信息损失。在ImageNet 256×256图像生成任务中，DisCon取得1.38的gFID得分，显著优于当前最先进自回归方法。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-based visual generation models inherently introduces information loss that degrades image fidelity. To mitigate this limitation, recent studies have explored to autoregressively predict continuous tokens. Unlike discrete tokens that reside in a structured and bounded space, continuous representations exist in an unbounded, high-dimensional space, making density estimation more challenging and increasing the risk of generating out-of-distribution artifacts. Based on the above findings, this work introduces DisCon (Discrete-Conditioned Continuous Autoregressive Model), a novel framework that reinterprets discrete tokens as conditional signals rather than generation targets. By modeling the conditional probability of continuous representations conditioned on discrete tokens, DisCon circumvents the optimization challenges of continuous token modeling while avoiding the information loss caused by quantization. DisCon achieves a gFID score of 1.38 on ImageNet 256$\times$256 generation, outperforming state-of-the-art autoregressive approaches by a clear margin. Project page: https://pengzheng0707.github.io/DisCon.
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。