Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
- 类型：arxiv
- 标识：2608.19567
- 链接：https://arxiv.org/abs/2608.19567
- 主分类：multimodal
- 形态：method
- TLDR：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 s
- 待LLM分类：否
- 标题中文：Block3D：通过块级扩散实现高效文本到 3D 生成
- TLDR中文：尽管文本到 3D 生成进展迅速，在低推理成本下实现高几何保真度仍具挑战。现有文本到 3D 方法要么自回归地解码离散形状 token，要么通过扩散或流模型迭代优化全局 3D 表示。然而，自回归解码是顺序执行的且无法修正错误，而扩散与流匹配模型反复处理完整表示，使高质量生成成本日益高昂。本文提出 Block3D，一种块级扩散框架，将离散 s
- 来源文件：
- /inbox/tom/_candidates/2026-08-25-agent-rag-longcontext-candidates.json