通过逐层筛选高质量图像片段，提升视觉自回归生成质量。
LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling
- 在每一尺度上采样多个候选图像块，用轻量评分模型选出最优
- 使VAR模型生成图像的FID从1.95降至1.66，仅增加1%推理时间
- 适合追求高质图像且计算资源有限的生成任务
视觉自回归（VAR）模型通过跨层级并行解码多标记实现图像生成，兼顾高质量与高效性。然而，同一尺度内并行采样可能导致结构错误。为此，本文提出潜空间拒绝采样（LSRS），在推理过程中逐步优化潜空间的标记图。该方法在每个尺度上采样多个候选标记图，由轻量评分模型评估并选择优质图，引导后续尺度生成。通过优先优化关键早期尺度，有效缓解自回归误差累积，同时保持高效。实验表明，对于VAR-d30模型，LSRS仅使推理时间增加1%，FID从1.95降至1.78；当推理时间增加15%时，FID可进一步降至1.66。该方法为基于VAR的生成提供了高效的测试时扩展方案。
原文摘要 · Abstract (English)
Visual Autoregressive (VAR) modeling approach for image generation proposes autoregressive processing across hierarchical scales, decoding multiple tokens per scale in parallel. This method achieves high-quality generation while accelerating synthesis. However, parallel token sampling within a scale may lead to structural errors, resulting in suboptimal generated images. To mitigate this, we propose Latent Scale Rejection Sampling (LSRS), a method that progressively refines token maps in the latent scale during inference to enhance VAR models. Our method uses a lightweight scoring model to evaluate multiple candidate token maps sampled at each scale, selecting the high-quality map to guide subsequent scale generation. By prioritizing early scales critical for structural coherence, LSRS effectively mitigates autoregressive error accumulation while maintaining computational efficiency. Experiments demonstrate that LSRS significantly improves VAR's generation quality with minimal additional computational overhead. For the VAR-d30 model, LSRS increases the inference time by merely 1% while reducing its FID score from 1.95 to 1.78. When the inference time is increased by 15%, the FID score can be further reduced to 1.66. LSRS offers an efficient test-time scaling solution for enhancing VAR-based 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。