用正交视图引导重建CAD建模步骤，更贴近人类设计过程。
SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction
- 分步观察正交投影与草图，实现实时视觉反馈决策。
- 在12个模型上重建准确率超基线37.6%，仅需少量数据。
- 适合需要还原设计逻辑的工业设计与逆向工程场景。
从图像中重建计算机辅助设计（CAD）建模序列对于保留设计意图和支撑参数化编辑至关重要。然而，现有方法通常整体生成完整建模序列，忽略了人类设计流程中迭代与反馈的特性。本文提出一种分步视觉监督机制：在每个建模步骤中，系统观察目标的正交投影、逐步构建模型的投影以及当前草图，从而做出更明智的操作选择。为此，我们提出SOV-CAD框架，将建模序列重建建模为顺序决策问题，并采用基于决策变换器架构的离线强化学习。该设计通过几何对齐奖励实现连续视觉反馈，使重建过程更精确且更接近人类行为。大量实验表明，SOV-CAD在多个测试模型上的重建准确率优于现有最优方法，同时展现出优异的数据效率。代码已公开于：https://github.com/LukePhong/SOV-CAD
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。