用分块扩散加速文本生成3D，速度提升5倍且保持精度
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
- 将3D形状序列分块，分块内并行去噪，块间自回归生成
- 在TRELLIS-500K数据集上推理时间从25.71秒降至4.99秒
- 引入置信度引导的块内纠错，缓解误差累积问题
尽管文本到3D生成进展迅速，但在低推理成本下实现高几何保真度仍具挑战。现有方法要么逐个解码离散形状令牌，要么通过扩散或流匹配模型迭代优化全局3D表示。然而，自回归解码是顺序进行且无法修正错误，而扩散与流匹配模型反复处理完整表示，导致高质量生成成本不断上升。本文提出Block3D，一种分块扩散框架：将离散形状令牌序列划分为连续块，分块自回归生成，并联合去噪当前块内所有令牌。为缓解误差累积，引入置信度引导的块内纠正机制，在每块定稿前修正低置信度令牌。在TRELLIS-500K的保留测试集上，Block3D将平均端到端生成时间从25.71秒降低至4.99秒，相较微调后的自回归基线实现5.15倍提速，且未牺牲几何保真度。
原文摘要 · Abstract (English)
While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decode discrete shape tokens autoregressively or iteratively refine global 3D representations with diffusion or flow models. However, autoregressive decoding is sequential and cannot revise errors, whereas diffusion and flow-matching models repeatedly process the full representation, making high-quality generation increasingly expensive. In this paper, we propose Block3D, a block-wise diffusion framework that partitions the discrete shape-token sequence into contiguous blocks, generates the blocks autoregressively, and jointly denoises all tokens within the current block. To alleviate error accumulation, we introduce confidence-guided intra-block correction, which revises low-confidence tokens before each block is finalized. On a held-out set from TRELLIS-500K, Block3D reduces mean end-to-end generation time from 25.71 seconds to 4.99 seconds, achieving a $5.15\times$ speedup over the fine-tuned autoregressive baseline without sacrificing geometric fidelity.
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。