CVQ解决了传统VQ码本利用率低、细节丢失的痛点，做图像生成和视觉自回归研究的开发者值得关注——它让模型像人类一样先画轮廓再细化，生成质量更高。
本文提出通道级向量量化（CVQ），一种全新的图像标记化范式，将传统基于空间分块的标记方式改为对特征图每个通道进行量化。基于CVQ，作者构建了通道级自回归（CAR）模型，采用“下一通道预测”策略，模拟人类艺术家先画轮廓再细化细节的创作流程。实验表明，CVQ在16K+码本大小下实现100%码本利用率，显著提升重建质量；CAR在DPG和GenEval指标上分别达到86.7和0.79，在文本到图像生成任务中表现强劲。这一工作为视觉自回归模型提供了新思路，有望推动图像生成效率与质量的双重提升。
Channel-wise Vector Quantization
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.