Zhaopeng Feng, Chen Zhi
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.
@article{de19cc48-d86b-4b7f-8eeb-b1a4c4cdba80,
title={SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction},
author={Zhaopeng Feng and Chen Zhi},
year={2025},
language={en}
}TY - JOUR TI - SOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction AU - Zhaopeng Feng AU - Chen Zhi PY - 2025 LA - en ER -
Siddhartha Mukherjee
This book provides a comprehensive overview of the critical aspects of industrial process engineering and plant design, addressing the complexities an
David Pollard, Geoff Dunlop
The MetPlant 2008 conference focused on advancements in metallurgical processing of ores, emphasizing plant design, operation strategies, and innovati
Rajesh Jha, Bimal Kumar Jha
This book describes the application of artificial intelligence (AI) and machine learning (ML) concepts to develop predictive models that can be used t
Unknown, Unknown
This study focuses on the fundamental characteristics of solid iron, which is predominantly composed of iron atoms and provides a basis for understand
Unknown, Unknown
This chapter discusses metal casting processes, highlighting the diversity and common characteristics among them. The objective is to elucidate the fu
This paper addresses the challenge of assessing the feasibility of wind power plant projects at sites with insufficient or no local historic wind data