面向参数化 CAD 草图的双向查询驱动生成
Bidirectional Query-Driven Generation of Parametric CAD Sketch
把参数化草图序列当作可双向查询的序列建模对象，用置信度门控决定向前/向后扩展方向，并用有效性编译器保证生成指令可执行——这套「双向自回归 + 可执行性校验」思路可迁移到矢量图形、笔刷序列、程序化场景布局等结构化序列生成任务。
原文依据 a bidirectional sketch learner recovers both prior and posterior contexts from arbitrary-span partial sketches via a bidirectional query mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于学习的 CAD 建模在自动化参数化设计方面展现出巨大潜力，但现有方法往往忽视了草图构建的增量性与状态依赖性。本文提出 CADSketcher，一个查询驱动的双向框架，通过内化交互式 CAD 过程中的非线性构建逻辑，来完成不完整的参数化草图。CADSketcher 的核心包含两项关键创新。第一，双向草图学习器通过双向查询机制，从任意跨度的不完整草图中同时恢复先验与后验上下文，从而能够探索多条合理的建模轨迹。第二，置信度引导的补全流程通过置信度门控自适应地确定扩展方向，并利用有效性编译器确保生成可执行的指令，同时渐进式上下文更新器在草图状态不断演化的过程中保持草图的一致性。此外，混合位置编码将全局建模进程与局部几何语义相结合，在学习与补全两个阶段均强化了结构连贯性。大量实验表明，CADSketcher 在多种草图补全任务上取得了更优的几何有效性与指令一致性，为智能 CAD 自动化提供了一个稳健且可解释的框架。
英文原文摘要 1362 字符
Learning-based CAD modeling shows great promise in automating parametric design, yet existing approaches often overlook the incremental and state-dependent nature of sketch construction. We present CADSketcher, a query-driven bidirectional framework for completing partial parametric sketches by internalizing the non-linear construction logic of interactive CAD processes. At the core of CADSketcher are two key innovations. First, a bidirectional sketch learner recovers both prior and posterior contexts from arbitrary-span partial sketches via a bidirectional query mechanism, enabling exploration of multiple plausible modeling trajectories. Second, a confidence-guided completion pipeline adaptively determines the expansion direction through a confidence gate and ensures executable instruction generation using a validity compiler, while a progressive context updater preserves sketch consistency throughout the evolving sketch state. In addition, a hybrid positional encoding integrates global modeling progression with local geometric semantics, reinforcing structural coherence during both learning and completion. Extensive experiments demonstrate that CADSketcher achieves superior geometric validity and instruction consistency across diverse sketch completion tasks, offering a robust and interpretable framework toward intelligent CAD automation.