发表机构
School of Software Technology, Zhejiang University; Zhejiang Key Laboratory of Digital-Intelligence Service Technology, Zhejiang University; ZWSOFT Co., Ltd.（浙江大学软件学院; 浙江大学数字智能服务技术重点实验室; ZWSOFT公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究从图像重建CAD建模序列，引入逐步视觉监督，提出SOV-CAD框架将其作为序列决策任务，用离线强化学习及决策变压器架构，利用几何对齐奖励的视觉反馈，提升重建准确性与数据效率。
AI 中文摘要
从图像重建计算机辅助设计（CAD）建模序列对于保留设计意图和支持参数编辑至关重要。现有方法通常整体生成完整的CAD序列，忽略了人类设计工作流程的迭代、反馈驱动性质。我们通过引入丰富的逐步视觉监督来解决这一限制：在每个建模步骤中，系统观察目标的正交投影、增量构建模型的投影和活动草图，从而实现明智的动作选择。为了有效地利用这种实时反馈，我们提出了SOV-CAD，这是一个将CAD重建制定为顺序决策任务的框架，并采用具有决策变压器架构的离线强化学习。这种设计结合了由几何对齐奖励引导的连续视觉反馈，从而产生更准确和更像人类的建模过程。广泛的实验表明，SOV-CAD在CAD序列重建方面超越了现有方法，同时表现出强大的数据效率。SOV-CAD的代码可在以下网址获得：此https URL
英文摘要
Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. However, existing methods typically generate full CAD sequences holistically, overlooking the iterative, feedback-driven nature of human design workflows. We address this limitation by introducing the rich stepwise visual supervision: at each modeling step, the system observes the target's orthographic projections, the projections of the incrementally constructed model, and the active sketch, enabling informed action selection. To effectively leverage this on-the-fly feedback, we propose SOV-CAD, a framework that formulates CAD reconstruction as a sequential decision-making task and employs offline reinforcement learning with a Decision Transformer architecture. This design incorporates continuous visual feedback guided by geometric alignment rewards, resulting in a more accurate and human-like modeling process. Extensive experiments show that SOV-CAD surpasses state-of-the-art methods in CAD sequence reconstruction while exhibiting strong data efficiency. Code of SOV-CAD is available at: https://github.com/LukePhong/SOV-CAD
CommentsAccepted to ICME 2026
