InsightTok: 提高离散分词中文本和面部保真度以用于自回归图像生成
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
AI总结：
InsightTok通过局部内容感知损失提升文本和面部保真度，在不牺牲通用重建质量的情况下优于现有分词器，从而推动离散图像生成的发展。
摘要：
文本和面孔是视觉生成中最显著且实用的模式，但它们仍然是基于离散分词的自回归生成器的挑战。核心瓶颈是分词器：激进的下采样和量化常常丢弃需要保留可读字符和独特面部特征的细粒度结构。我们归因于标准离散分词目标与文本可读性和面部保真度的弱对齐，因为这些目标通常优化通用重建，同时均匀压缩多样化内容。为了解决这个问题，我们提出了InsightTok，一个简单而有效的离散视觉分词框架，通过局部化、内容感知的感知损失来增强文本和面部保真度。使用紧凑的16k代码本和16倍下采样率，InsightTok在文本和面部重建方面显著优于现有分词器，而不影响通用重建质量。这些收益一致转移到InsightAR中的自回归图像生成中，产生具有更清晰文本和更忠实面部细节的图像。总体而言，我们的结果突显了在分词器训练中使用专门监督的潜力，以推动离散图像生成的发展。
英文摘要：
Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features. We attribute this gap to standard discrete-tokenizer objectives being weakly aligned with text legibility and facial fidelity, as these objectives typically optimize generic reconstruction while compressing diverse content uniformly. To address this, we propose InsightTok, a simple yet effective discrete visual tokenization framework that enhances text and face fidelity through localized, content-aware perceptual losses. With a compact 16k codebook and a 16x downsampling rate, InsightTok significantly outperforms prior tokenizers in text and face reconstruction without compromising general reconstruction quality. These gains consistently transfer to autoregressive image generation in InsightAR, producing images with clearer text and more faithful facial details. Overall, our results highlight the potential of specialized supervision in tokenizer training for advancing discrete image generation.
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。
