让自回归图像生成可迭代优化，提升生成质量。
From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
- 改用滑动窗口预测图像张量，实现内容迭代修正。
- 在LlamaGEN等模型上显著提升图像生成质量。
- 无需改动原有结构，可直接插入现有模型使用。
自回归（AR）图像生成通过逐个预测离散图像标记，提供类语言模型的生成方式。然而，与扩散模型不同，AR模型缺乏对先前预测结果的修正机制，限制了生成质量。本文提出TensorAR，一种新的自回归范式，将图像生成从下一标记预测重构为下一张量预测。通过以滑动方式生成重叠的图像块（张量），TensorAR实现了对已生成内容的迭代优化。为防止训练中信息泄露，提出基于码本索引的离散张量加噪方案，扰动输入标记。TensorAR作为即插即用模块，兼容现有AR模型。在LlamaGEN、Open-MAGVIT2和RAR上的大量实验表明，TensorAR显著提升了自回归模型的生成性能。
原文摘要 · Abstract (English)
Autoregressive (AR) image generators offer a language-model-friendly approach to image generation by predicting discrete image tokens in a causal sequence. However, unlike diffusion models, AR models lack a mechanism to refine previous predictions, limiting their generation quality. In this paper, we introduce TensorAR, a new AR paradigm that reformulates image generation from next-token prediction to next-tensor prediction. By generating overlapping windows of image patches (tensors) in a sliding fashion, TensorAR enables iterative refinement of previously generated content. To prevent information leakage during training, we propose a discrete tensor noising scheme, which perturbs input tokens via codebook-indexed noise. TensorAR is implemented as a plug-and-play module compatible with existing AR models. Extensive experiments on LlamaGEN, Open-MAGVIT2, and RAR demonstrate that TensorAR significantly improves the generation performance of autoregressive models.
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。