It is common to use computers to design shapes of physical objects such as furniture, but geometric modeling and the physical validity of shapes are conventionally considered independently. This makes creating aesthetically pleasing yet physically valid models challenging. In this paper, we propose an interactive design framework for the efficient and intuitive exploration of geometrically and physically valid shapes. During any geometric editing operation, the system continuously allows visualization of the valid range of the parameters being edited. When one or more constraints are violated following an operation, the system generates multiple suggestions involving both discrete and continuous changes to restore validity. Each suggestion is accompanied by an editing mode, which simultaneously adjusts multiple parameters in a coordinated manner to maintain validity. Thus, while the user focuses on the aesthetics of the design, our computational design framework helps to achieve physical realizability by providing active guidance to the user. We demonstrate our framework on plank-based furniture designs with nail-joints and frictional constraints. We use our system to design a range of examples, conduct a user study, and also fabricate a physical prototype to test its validity and usefulness.
Recent advances in three-dimensional (3D) modeling systems (such as the appearance of Blender and SketchUp) have enabled novice users to design complex shapes, thus making content creation widely accessible. However, along with aesthetic appeal of the designed shapes, the physical properties are often very important, particularly if the resulting model is to be fabricated and used in the real world. For example, in the context of do-it-yourself (DIY) furniture design, various physical constraints must be satisfied. For example, a chair is only useful if it remains stable and does not break with the target load distribution. However, current modeling systems typically do not consider such physical plausibility in the design phase. This makes creating interesting shapes that also satisfy physical constraints difficult for novice users, who may not have specialist knowledge or relevant experience.