CycleVAR：重新利用自回归模型进行无监督单步图像翻译
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
AI总结：
针对传统向量量化框架离散量化阻碍梯度流的问题，提出Softmax松弛量化保留梯度传播，进而构建CycleVAR模型，通过多尺度源图像标记实现图像条件自回归生成，其并行单步模式在无监督图像翻译中取得更优质量和更快速度，性能超越现有模型。
摘要：
当前的条件自回归图像生成方法已展现出良好效果，但其在无明确跨域对应关系的实际无监督图像翻译领域的潜力仍未被充分挖掘。传统基于向量量化（Vector Quantization）的框架中固有的离散量化存在关键局限性，会中断变分自动编码器（Variational Autoencoder）解码器与因果Transformer之间的梯度流，阻碍图像空间对抗训练期间的端到端优化。为解决此问题，我们提出使用Softmax松弛量化，这是一种通过Softmax将码本选择重构为连续概率混合过程的新方法，从而保留梯度传播。基于这一可微分基础，我们引入CycleVAR，通过注入多尺度源图像标记作为上下文提示，将图像到图像翻译重构为图像条件视觉自回归生成，类似于语言模型中基于前缀的条件设置。CycleVAR利用两种模式生成目标图像标记：（1）串行多步生成，支持跨尺度迭代优化；（2）并行单步生成，在单次前向传递中合成所有分辨率输出。实验结果表明，在无监督场景下，并行单步生成模式相比串行多步模式获得了更优的翻译质量和更快的推理速度。此外，定量和定性结果均显示CycleVAR优于此前的最先进无监督图像翻译模型（例如CycleGAN-Turbo）。
英文摘要：
The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image translation domain, which operates without explicit cross-domain correspondences. A critical limitation stems from the discrete quantization inherent in traditional Vector Quantization-based frameworks, which disrupts gradient flow between the Variational Autoencoder decoder and causal Transformer, impeding end-to-end optimization during adversarial training in image space. To tackle this issue, we propose using Softmax Relaxed Quantization, a novel approach that reformulates codebook selection as a continuous probability mixing process via Softmax, thereby preserving gradient propagation. Building upon this differentiable foundation, we introduce CycleVAR, which reformulates image-to-image translation as image-conditional visual autoregressive generation by injecting multi-scale source image tokens as contextual prompts, analogous to prefix-based conditioning in language models. CycleVAR exploits two modes to generate the target image tokens, including (1) serial multi-step generation, enabling iterative refinement across scales, and (2) parallel one-step generation synthesizing all resolution outputs in a single forward pass. Experimental findings indicate that the parallel one-step generation mode attains superior translation quality with quicker inference speed than the serial multi-step mode in unsupervised scenarios. Furthermore, both quantitative and qualitative results indicate that CycleVAR surpasses previous state-of-the-art unsupervised image translation models, \textit{e}.\textit{g}., CycleGAN-Turbo.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
