Interactive modeling of lofted shapes from a single image

Abstract

Modeling the complete geometry of general shapes from a single image is an ill-posed problem. User hints are often incorporated to resolve ambiguities and provide guidance during the modeling process. In this work, we present a novel interactive approach for extracting high-quality freeform shapes from a single image. This is inspired by the popular lofting technique in many CAD systems, and only requires minimal user input. Given an input image, the user only needs to sketch several projected cross sections, provide a "main axis", and specify some geometric relations. Our algorithm then automatically optimizes the common normal to the sections with respect to these constraints, and interpolates between the sections, resulting in a high-quality 3D model that conforms to both the original image and the user input. The entire modeling session is efficient and intuitive. We demonstrate the effectiveness of our approach based on qualitative tests on a variety of images, and quantitative comparisons with the ground truth using synthetic images.

The Model of Ceramic Surface Image Based on 3D Printing Technology

“…Aiming at the 3D printing technology of slurry direct writing ceramic, a screw structure instead of a needle barrel extrusion structure is proposed [14]. e formula of photosensitive resin paste is shown in Table 1.…”

Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches

“…Either of the two paradigms has its shortcomings: evocative methods are confined to generate certain shapes or primitives, and the lack of prior knowledge in constructive methods often requires large efforts to get the desired shape. Deng et al [6] proposed to extract free-form shapes from single images in an interactive way, inspired by the lofting technique in CAD systems. By utilizing deep learning techniques, several works [5,11,12,15,23,31,32,35,36] have achieved to gain priors from existing 3D models, while being able to leverage user inputs.…”