用通道级量化重构图像，像画家逐步添细节。
Channel-wise Vector Quantization
- 按通道而非图像块进行离散化，构建视觉细节层级
- 代码本利用率100%，重建质量显著优于传统方法
- 支持文本生成图像，效果达DPG 86.7、GenEval 0.79
我们提出通道级向量量化（CVQ），一种新型图像标记化范式，将传统的块级标记替换为通道级标记。与常规向量量化不同，CVQ对特征图的每个通道进行量化，将图像表示为视觉细节的离散层级，而非空间块网格。基于此，我们引入一种新的视觉自回归框架——通道级自回归（CAR），通过逐通道预测生成图像，先勾勒全局结构，再细化局部细节，模拟人类艺术家创作流程。实验表明：(1) CVQ在无额外优化情况下实现16K+代码本的100%利用率，重建质量显著优于传统VQ；(2) CAR模型在文本到图像生成任务中取得86.7的DPG分数和0.79的GenEval分数，展现出强大性能。
原文摘要 · Abstract (English)
We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This formulation represents an image as discrete levels of visual details, rather than as a grid of spatial patches. Based on CVQ, we introduce a new visual autoregressive framework with "next-channel prediction". Instead of rendering images patch by patch in raster order, our Channel-wise Autoregressive (CAR) model predicts image channels sequentially, producing progressively enriched visual details. Specifically, it first sketches global structure and then refines fine-grained attributes, akin to a human artist's workflow. Empirically, we show that: (1) CVQ achieves 100% codebook utilization with a 16K+ codebook size without any bells and whistles, and substantially improves reconstruction quality over conventional VQ; and (2) CAR attains a DPG score of 86.7 and a GenEval score of 0.79, demonstrating strong effectiveness for text-to-image generation.
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。