{"ID":2839654,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15618","arxiv_id":"2511.15618","title":"FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.15618","url_pdf":"https://arxiv.org/pdf/2511.15618v1","authors":"[\"Tingrui Shen\",\"Yiheng Zhang\",\"Chen Tang\",\"Chuan Ping\",\"Zixing Zhao\",\"Le Wan\",\"Yuwang Wang\",\"Ronggang Wang\",\"Shengfeng He\"]","published":"2025-11-19T17:03:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}