The Shape Modeling International (SMI 2018) Symposium is the premier international forum for the dissemination of new mathematical theories and novel computational techniques for modeling, simulating, and processing digital shape representations. SMI gathers a wide community of researchers, developers, practitioners, and students in academia and industry.
Conference proceedings will be published in a special issue of the Journal of Computers & Graphics (Elsevier) after a rigorous two-stage review process.
More information on topics, paper format, submission guidelines, and important dates are given below.
The Fabrication and Sculpting Event (FASE 2018) is organized in co-location with SMI 2018. It presents original research at the intersection of theory and practice in shape modeling, fabrication and sculpting. Visit FASE 2018 web page for more details.
Abstract for full papers: Wednesday, March 7th
Important Update: Although the abstract deadline has passed, we still accept full paper submissions on the EasyChair System until the full paper deadline.
Full paper submission: Monday, March 12th
First review notification: Friday, April 13th
Final notification of acceptance: Tuesday, May 8th
Poster submission: Friday, May 15th
Camera ready full papers due: Friday, May 15th
All deadlines at 23:59 UTC/GMT
Submissions should be formatted according to the style guidelines for Computers & Graphics (Elsevier) and should not exceed 12 pages, including figures and references, since all accepted papers will appear in a special issue of the said journal. We strongly recommend using the LaTeX template to format your paper. But we also accept papers formatted by MS Word according to the style guidelines for Computers & Graphics (Elsevier). The file must be submitted in PDF format for the first round of submission.
Double-Blind Review: The SMI 2018 conference will use a double-blind review process. Consequently, all submissions must be anonymous.
Abstract: An abstract should be submitted to the EasyChair System before March 7th at 23:59 UTC/GMT. The abstract should contain the title and one paragraph explaining the main idea of the paper. It will support the reviewer assignment.
Full Papers: All papers (maximum 12 pages) should be submitted to the EasyChair System before March 12th at 23:59 UTC/GMT.
Papers should present previously unpublished, original results that are not simultaneously submitted elsewhere.
All submission will be rigorously peer-reviewed by members of the international program committee. All accepted papers will be published in the journal of Computers & Graphics (Elsevier).
Any accepted paper is required to have at least one registered author to attend and present the paper at the conference.
If you have any technical problems on paper submission, please contact the Program Chairs for inquiry.
SMI-2018 will have a poster session and will accept proposals for posters in the form of abstracts. We encourage researchers and students to present to the SMI community their novel idea or work in a simple and concise manner.
We are now accepting abstract from poster submission form. Notification of poster acceptance will be sent out a.s.a.p. after reception of abstract. The submission will be closed by May 15th at 23:59 UTC/GMT.
The abstracts should contain the title, the names/affiliations/URLs of the authors, and a brief (at most 400 words) outline of the problem discussed and of the contribution presented.The display information and specifications (e.g., poster size) will be communicated along with the acceptance notifications to the authors.
Any accepted poster is required to have at least one registered author to attend and present the paper at the conference.
If you have any questions or suggestions, please contact poster session chair Xin (Shane) Li.
SMI participates in the Replicability Stamp Initiative, an additional recognition for authors who are willing to go one step further, and in addition to publishing the paper, provide a complete open-source implementation. The Graphics Replicability Stamp Initiative (GRSI) is an independent group of volunteers who want to help the community by enabling sharing of code and data as a community resource for non-commercial use. The volunteers review the submitted code and certify its replicability, awarding a replicability stamp, which is an additional recognition for authors of accepted papers who are willing to provide a complete implementation of their algorithm, to replicate the results presented in their paper. The replicability stamp is not meant to be a measure of the scientiﬁc quality of the paper or of the usefulness of presented algorithms. Rather, it is meant to be an endorsement of the replicability of the results presented in it!
The paper and the recognition of the service provided to the community by releasing the code. Submissions for the replicability stamp will be considered only after the paper has been fully accepted. Submissions that are awarded the replicability stamp will receive additional exposure by being listed on this website. The purpose of this stamp is to promote reproducibility of research results and to allow scientists and practitioners to immediately beneﬁt from state-of-the-art research results, without spending months re-implementing the proposed algorithms and trying to ﬁnd the right parameter values. We also hope that it will indirectly foster scientiﬁc progress, since it will allow researchers to reliably compare with and to build upon existing techniques, knowing that they are using exactly the same implementation. This is an initiative supported by a growing list of publishers, journals, and conferences.
The submission procedure is lightweight (click here to see requirements) and we encourage the authors of accepted papers to participate by filling the form that they received in the acceptance letter. The papers with the replicability stamp will receive additional exposure during SMI, and will be listed on the replicability stamp website.
The qualified papers will be decorated with the logo in the program
(logo design by Michela Mortara)
|until May 15th||after May 15th|
|Full Registration, IEEE, EG, ACM Member||€ 385||€ 495|
|Student Registration, IEEE, EG, ACM Member||€ 275||€ 330|
|Full Registration||€ 495||€ 605|
|Student Registration||€ 330||€ 385|
Bio: Hao (Richard) Zhang is a professor in the School of Computing Science at Simon Fraser University (SFU), Canada, where he directs the computer graphics (GrUVi) lab and the Professional Masters Program in Visual Computing. He obtained his Ph.D. from the University of Toronto and MMath and BMath degrees from the University of Waterloo. Richard's research is in computer graphics with special interests in geometric modeling, shape analysis, 3D content creation, as well as computational design and fabrication. He was a past editor-in-chief of Computer Graphics Forum, a SIGGRAPH Asia 2014 course chair, and paper chairs for SGP 2013, Graphics Interface 2015, CGI 2018, among others. He received a National Science and Engineering Research Council of Canada Discovery Accelerator Award in 2014, best paper awards from SGP 2008 and CAD/Graphics 2017, a Faculty Research Excellence Award at SFU in 2014, and a National Science Foundation of China (NSFC) Outstanding Overseas Scholar Award in 2015. He has been a visiting professor at Stanford University, Shandong University, and Shenzhen University.
Abstract: Symmetry is ubiquitous in nature and man-made artifacts. In this talk, I first explain how symmetry organization can play a crucial role in understanding shapes and patterns. In particular, it may seem surprising that one can infer the generative history of a pattern by analyzing its symmetries alone. Furthermore, I show how a symmetry-induced hierarchical representation of shape structures holds the key to allow a machine to learn a generative model of 3D shapes. However, symmetry analysis is only a start, I argue that the ultimate goal of shape understanding is a functional understanding. With an intimate connection to object functionality, symmetry provides a first cue (i.e., symmetric object parts tend to perform the same function) to functional shape analysis, but the missing piece is how an object interacts with its environment to perform its functions. In the second part of my talk, I will introduce our recent works on functional analysis and modeling of 3D shapes, evolving from a descriptor of static functionalities to functional motion prediction, and from model-driven approaches to the utilization of deep neural networks.
Bio: Baining Guo is a Distinguished Scientist with the Microsoft Corporation and Deputy Managing Director of Microsoft Research Asia, where he also serves as the head of the computer graphics lab. Prior to joining Microsoft in 1999, Baining was a senior staff researcher with Intel Research in Santa Clara, California. Baining received his PhD and MS degrees from Cornell University, and his BS from Beijing University. He is a fellow of ACM and IEEE. Baining works in computer graphics and computer vision. His interests span most aspects of computer graphics, with an emphasis on statistical modeling of texture and appearance, GPU-based rendering, and geometric modeling. He has also worked on image understanding and video analysis. He was on the editorial boards of IEEE Transactions on Visualization and Computer Graphics, Elsevier Journal of Computer and Graphics, and IEEE Computer Graphics and Applications. He has also served on program committees of most major graphics and visualization conferences, including ACM SIGGRAPH, ACM SIGGRAPH Asia, and IEEE Visualization. In 2014, he was the technical papers chair of ACM SIGGRAPH Asia. Dr. Guo has over 50 US patents.
Abstract: The dependence on representations is a general phenomenon that appears throughout geometric computing. In 3D shape retrieval, for example, searching a target shape can proceed exponentially faster if the shapes database is well structured and properly indexed. It is not surprising that the choice of shape representation has an enormous eﬀect on the performance of geometry processing algorithms. In this talk, I will review both the conventional shape representations (parametric surfaces, implicit surfaces, and meshes) and the emerging distributed shape representations. I will discuss the impact of distributed shape representations on the future of 3D shape analysis and synthesis.