image: A lamp and a chair fully automatically synthesized by component in the database. view more
Credit: SIGRAPH ASIA
BANGKOK, THAILAND, Geometric modeling is essential for populating virtual environments and designing real objects, ranging from furniture and car assembly to 3D modeling of chemical compounds and medical devices. Yet creating 3D models from scratch are tedious and a time-consuming process that typically requires expertise.
Researchers from Stanford University, University of California at San Diego, Adobe Research and IIT Bombay have collaborated on a novel computational framework for assembly-based 3D modeling that automatically suggests to users (of any skill level) which parts to use and where to place the part in the actual design.
Coauthors of the research, ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling, are set to present their work at SIGGRAPH Asia 2017 in Bangkok, 27 to 30 November. The annual conference and exhibition showcase the world's leading professionals, academics and creative minds at the forefront of computer graphics and interactive techniques.
Given a partial object, for example, a basic chair back, the team's method proposes a set of potential complementary components from a repository of 3D shapes, such as the seat and chair legs. In examples, the researchers were able to show that their method automatically suggests complementary parts based on any shape proposed. Not only are the parts suggested but the placement in the assembly as well; for instance, in designing a desk, the method can automatically predict whether the next step in the process is to add a drawer, and furthermore, whether that drawer should be placed in the center of the table, the left-hand side or the right-hand side.
If a user wants more design control, however, the method provides an interactive capability. Given a partial assembly, for example, part of a sofa or a basic shape of a sofa, the algorithm first proposes a set of possible components, then, the user gets to choose which component to use in their design. The method predicts where that piece is placed. When evaluated, their new approach demonstrated significant improvement over state-of-the-art retrieval techniques.
"Our method leads to a modeling tool that requires minimal or no user inputs" said Minhyuk Sung, lead author and a computer science PhD student at Stanford, advised by coauthor Leonidas Guibas, professor of computer science and electrical engineering at Stanford. "We've come up with novel solutions to two key technical components in assembly-based modeling: part retrieval and part placement."
A key contribution of their research is that the method allows users to pull unlabeled data obtained from anywhere on the Internet, making the process of automating 3D model design more efficient. Existing techniques for computational design of 3D models typically include a detailed step for labeling and indexing parts required for design. The new technique does not require the models used to train the algorithm to be consistently segmented into labeled parts. Instead, it can learn from un-annotated, inconsistently segmented collections of models in online repositories.
In future work, the researchers plan to augment their framework with capabilities to further manipulate and customize retrieved parts, providing even better compatibility with the initial query. To make the modeling process even more interactive and intuitive, the researchers intend to add more fine-grained suggestions: for instance, parts with specific attributes such as surface roughness or aesthetic style.
###
Sung and Guibas collaborated on the work with Hao Su, assistant professor at UC San Diego; Vladimir G. Kim, research scientist at Adobe; and Siddhartha Chaudhuri, senior research scientist at Adobe and assistant professor of computer science at IIT Bombay.
About SIGGRAPH Asia 2017
The 10th ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia will take place in Bangkok, Thailand at the at the Bangkok International Trade and Exhibition Centre (BITEC) from 27 - 30 November 2017. The annual event held in Asia attracts the most respected technical and creative people from all over the world who are excited by research, science, art, animation, gaming, interactivity, education and emerging technologies. The four-day SIGGRAPH Asia 2017 conference includes a diverse range of juried programs, such as the Art Gallery, Computer Animation Festival, Courses, Emerging Technologies, Posters, Symposium on Education, Symposium on Mobile Graphics and Interactive Applications, Symposium on Visualization, Technical Briefs, Technical Papers, VR Showcase and Workshops. A three-day exhibition held from 28 - 30 November 2017 will offer a business platform for industry players to market their innovative products and services to the computer graphics and interactive techniques professionals and enthusiasts from Asia and beyond.
About ACM SIGGRAPH
The Association of Computing Machinery's Special Interest Group on Computer Graphics and Interactive Techniques (ACM SIGGRAPH) sponsors SIGGRAPH Asia 2017. Founded in 1947, ACM is an educational and scientific society uniting the world's computing educators, researchers, and professionals to inspire dialogue, share resources, and address the field's challenges. ACM strengthens the profession's collective voice through strong leadership, promotion of the highest standards, and recognition of technical excellence. The ACM SIGGRAPH deals with all aspects of graphical user/computer communication and manipulation: hardware, languages, data structure, methodology, and applications