{"ID":5937606,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T05:08:25.597675483Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04119","arxiv_id":"2607.04119","title":"SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction","abstract":"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","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.04119","url_pdf":"https://arxiv.org/pdf/2607.04119v1","authors":"[\"Zhaopeng Feng\",\"Chen Zhi\",\"Xuhong Zhang\",\"Zhengwen Feng\",\"Xinkui Zhao\"]","published":"2026-07-05T05:12:58Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Transformer\"]","has_code":false,"code_links":[{"ID":613972,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5937606,"paper_url":"https://arxiv.org/abs/2607.04119","paper_title":"SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction","repo_url":"https://github.com/LukePhong/SOV-CAD","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}