FlashMesh: 通过结构化猜测实现更快更好的自回归网格合成
FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
AI总结：
FlashMesh通过结构化猜测方法，实现更快更高质量的网格生成，提升自回归模型的效率和保真度。
摘要：
自回归模型可以通过依次生成顶点和面来生成高质量的3D网格，但其逐token解码会导致推理缓慢，限制了在交互式和大规模应用中的实际使用。我们提出了FlashMesh，一种快速且高保真的网格生成框架，通过预测-校正-验证范式重新思考自回归解码。关键思路是网格token表现出强结构和几何相关性，这使得多token猜测具有信心。FlashMesh通过引入一种针对常用hourglass transformer架构定制的猜测解码方案，实现了在面、点和坐标层面的并行预测。大量实验表明，FlashMesh在标准自回归模型上实现了高达2倍的速度提升，同时提高了生成保真度。我们的结果表明，网格数据中的结构先验可以系统地用于加速和增强自回归生成。
英文摘要：
Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in interactive and large-scale applications. We present FlashMesh, a fast and high-fidelity mesh generation framework that rethinks autoregressive decoding through a predict-correct-verify paradigm. The key insight is that mesh tokens exhibit strong structural and geometric correlations that enable confident multi-token speculation. FlashMesh leverages this by introducing a speculative decoding scheme tailored to the commonly used hourglass transformer architecture, enabling parallel prediction across face, point, and coordinate levels. Extensive experiments show that FlashMesh achieves up to a 2 x speedup over standard autoregressive models while also improving generation fidelity. Our results demonstrate that structural priors in mesh data can be systematically harnessed to accelerate and enhance autoregressive 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。
