We are an inter-disciplinary team of researchers working in visual computing, in particular, computer graphics and computer vision. Current areas of focus include 3D and robotic vision, 3D printing and content creation, animation, AR/VR, geometric and image-based modelling, machine learning, natural phenomenon, and shape analysis. Our research works frequently appear in top venues such as SIGGRAPH, CVPR, and ICCV (we rank #10 in the world in terms of top publications in visual computing, as of 7/2019) and we collaborate widely with the industry and academia (e.g., Adobe Research, Google, MSRA, Princeton, Stanford, and Washington). Our faculty and students have won numerous honours and awards, including FRSC, Alain Fournier Best Thesis Award, Google Faculty Award, TR35@Singapore, NSERC Discovery Accelerator, and six best paper awards from ECCV, SCA, SGP, etc. Gruvi alumni went on to take up faculty positions in Canada, the US, and Asia, while others now work at companies including Apple, EA, Facebook, Google, IBM, and Microsoft.
Jul 23, 2019
The International Geometry Summit (IGS) 2019, organized by Richard Zhang and Ali Mahdavi-Amiri, took place from 17th June to the 21th June 2019 at SFU Harbour Center in Vancouver, Canada. IGS 2019 included four conferences: the Symposium on Solid and Physical Modelling, Shape Modeling International, SIAM Conference on Computational Geometric Design, and International Conference on Geometric Modelling and Processing. IGS 2019 featured state of the art researches in its technical paper sessions along with 12 keynote speeches from prominent researchers in the area of geometry.
Congratulations to Richard Zhang and Ali Mahdavi-Amiri for the successful organization and thanks to all GrUVi students that volunteered to make IGS’19 a success!
Jul 23, 2019
The International Geometry Summit (IGS) 2019, organized by Richard Zhang and Ali Mahdavi-Amiri, took place from 17th June to the 21th June 2019 at SFU Harbour Center in Vancouver, Canada. IGS 2019 included four conferences: the Symposium on Solid and Physical Modelling, Shape Modeling International, SIAM Conference on Computational Geometric Design, and International Conference on Geometric Modelling and Processing. IGS 2019 featured state of the art researches in its technical paper sessions along with 12 keynote speeches from prominent researchers in the area of geometry.Congratulations to Richard Zhang and Ali Mahdavi-Amiri for the successful organization and thanks to all GrUVi students that volunteered to make IGS’19 a success!
Jul 22, 2019
Richard Zhang was featured in the Eurographics Symposium on Geometry Processing (SGP) as a keynote speaker! His speech was titled “Can Machines Learn to Generate 3D Shapes?”.
In his talk, Richard highlighted the representation, data, and output challenges that researchers must tackle and how his research has shaped itself to address these challenges.
One of the key issues in this domain is not generate shapes that look right; instead, they need to serve their intended function while displaying the right part connections, arrangements, and geometry.
Jul 22, 2019
Richard Zhang was featured in the Eurographics Symposium on Geometry Processing (SGP) as a keynote speaker! His speech was titled “Can Machines Learn to Generate 3D Shapes?”.In his talk, Richard highlighted the representation, data, and output challenges that researchers must tackle and how his research has shaped itself to address these challenges.One of the key issues in this domain is not generate shapes that look right; instead, they need to serve their intended function while displaying the right part connections, arrangements, and geometry.
Jul 9, 2019
<a href”http://www.cse.msu.edu/~liuxm” target=”_blank”>Dr. Xiaoming Liu</a> visited SFU today following an invitation from Dr. Yasutaka Furukawa! His talk titled “Inverse Graphics for 3D Modeling and Reconstruction: from Face to Generic Objects” has the following abstract:
“Reconstructing the detailed and complete 3D surface of an object from a single 2D image is a long standing computer vision problem. In this talk, we present an inverse graphics-based framework to learn a 3D face model from a large set of in-the-wild 2D face images, without the need of capturing 3D scans. We also extend this framework to high-fidelity face modeling, as well as generic object modeling and 3D reconstruction. In the end, we will briefly overview other research efforts in the Computer Vision Lab at Michigan State University, including face anti-spoofing, explainable recognition, early sensor fusion of LiDAR and RGB, 2D/3D object detection from urban driving videos, etc.”
Jul 9, 2019
Dr. Xiaoming Liu visited SFU today following an invitation from Dr. Yasutaka Furukawa! His talk titled “Inverse Graphics for 3D Modeling and Reconstruction: from Face to Generic Objects” has the following abstract: “Reconstructing the detailed and complete 3D surface of an object from a single 2D image is a long standing computer vision problem. In this talk, we present an inverse graphics-based framework to learn a 3D face model from a large set of in-the-wild 2D face images, without the need of capturing 3D scans. We also extend this framework to high-fidelity face modeling, as well as generic object modeling and 3D reconstruction. In the end, we will briefly overview other research efforts in the Computer Vision Lab at Michigan State University, including face anti-spoofing, explainable recognition, early sensor fusion of LiDAR and RGB, 2D/3D object detection from urban driving videos, etc.”
Jul 3, 2019
GrUVi is glad to announce that Yagiz Aksoy will join our team this August. He is a PhD student of Marc Pollefeys at ETH Zurich. During his PhD, he spent a year at MIT CSAIL working with Wojciech Matusik and three years at Disney Research Zurich.
His research is at the intersection of computer vision and computer graphics, focusing on analyzing images to allow for realistic manipulation of photographs. His research has resulted in publications at venues such as SIGGRAPH, CVPR, and ACM Transactions on Graphics.
Welcome to the GrUVi team, Yagiz!
Jul 3, 2019
GrUVi is glad to announce that Yagiz Aksoy will join our team this August. He is a PhD student of Marc Pollefeys at ETH Zurich. During his PhD, he spent a year at MIT CSAIL working with Wojciech Matusik and three years at Disney Research Zurich.His research is at the intersection of computer vision and computer graphics, focusing on analyzing images to allow for realistic manipulation of photographs. His research has resulted in publications at venues such as SIGGRAPH, CVPR, and ACM Transactions on Graphics.Welcome to the GrUVi team, Yagiz!
Jun 3, 2019
The GrUVi team congratulates both Zhiqin and Jon for their sucessful MSc theses defense!
Jon's thesis is on A Qualitative and Localized Evaluation for 3D Indoor Scene Synthesis
Zhiqin's thesis is on IM-NET: Learning Implicit Fields for Generative Shape Modeling
Zhiqin's thesis defence also received the honor of "pass as is" today. Both of them will start as PhDs at GrUVi this September.
May 23, 2019
The GrUVi team congratulates Kangxue Yin, whom received the prestigious Chinese Government Award for Outstanding Self-financed Students Abroad!
This award was established in 2003 by the China Scholarship Council. The worldwide recipients are chosen annually based on a record of outstanding accomplishments in any discipline.
This award is considered the highest award given by Chinese government for Chinese graduate students studying abroad who do not receive regular financial support from Chinese government.
Currently, this award is granted to only 500 students every year. Since there are around half a million Chinese students to study abroad per year, this a highly competitive award. For the academic year 2018, only 6 awardees were based in British Columbia, Canada. Among them, Kangxue was the only student majoring in Computer Science.
May 1, 2019
A paper by Zhiqin Chen and Hao Zhang on learning implicit fields for generative modeling of 3D shapes will be presented at CVPR 2019!
It has also been invited to be presented at the Workshop on 3D Scene Generation at CVPR; see paper on arXiv.
Congratulations to both Zhiqin and Richard!
April 14, 2019
The GrUVi team would like to welcome three SFU undergrad students who are joining the lab for summer/visiting research:
In addition, Xiaogang Wang is joining us as a visiting PhD from Beihang University, the same university as Jiongchao. He comes with an already impressive research record (one SIG Asia and one CVPR), working with Kevin, a GrUVi alumni himself.
Fenggen (Fogg) Yu, will be a new PhD starting this fall. Fenggen is from Nanjing University and he had already collaborated with GrUVi members on a ACM TOG paper. He also has a CVPR paper this year.
We are also pleased to announce that two current members of the lab, Zhiqin and Jon, will continue as PhD students this fall.
Finally, Akshay is returning from his internship at Amazon (Israel) and Manyi, as a newly minted PhD, will be back as a postdoc this Summer.
October 2, 2018
GrUVi members co-author five technical papers at SIGGRAPH Asia 2018, which will be held at Tokyo in December 4-7. In particular, Wallace, Shuhua, Akshay, Manyi, Ali, and Han all got their very first SIG papers! The papers cover topics in fabrication, machine learning, shape and scene modeling, NLP, and even a fun (fabricable) puzzle! The papers are: "Language-Driven Synthesis of 3D Scenes Using Scene Databases", "Construction and Fabrication of Reversible Shape Transforms", "Fabricable Eulerian Wires for 3D Shape Abstraction", "SCORES: Shape Composition with Recursive Substructure Priors", and "3D Fabrication with Universal Building Blocks and Pyramidal Shells". Congratulations to all authors!
August 23, 2018
Two gruviers were student volunteers (SV) at the SIGGRAPH 2018 conference. While the attendees were certainly thankful for all the work that all the volunteers put in the event, our gruvi volunteers described how valuable the experience was for them! Zhiqin got the chance to use the hardware available at the exhibition hall to print the awesome gruvi logo on the hat shown in the picture. He described the great impact that experiencing the latest developments on VR technology had on him:
"I'm honored to be a student volunteer of such a great conference. VR was definitely a highlight of SIGGRAPH 2018. There were many showcases of applying haptic technology to VR and utilizing VR for designing and creating content. The immersive pavilion was awesome and provided me all kinds of VR experiences. I am looking forward to next SIGGRAPH!"
Akshay, on the other hand, emphasized the connections he was able to forge during his time as a volunteer:
"This was my first SIGGRAPH and my first time as a SIG-SV. The kind of atmosphere, the exuberance of energy and experience that I felt was surreal and I was left wanting for more when it ended. Memories of a lifetime with awesome fellow SV's, coordinating various programs and above all, the latest technology!! Definitely want to relive this again at SIG'19."
August 21, 2018
SIGGRAPH 2018 was held in Vancouver from August 12 to 16, at the Vancouver Convention Centre. The majority of GrUVi members attended the conference, some as paper presenters and some as student volunteers. This year, the lab contributed four papers that were presented in the Technical Papers program. Ali presented his paper on semi-supervised analysis of 3D shape styles and Kangxue presented his paper on P2P-NET, both on Thursday, in the paper session on Shape Analysis. Also notably, long-term collaborator with GrUVi and adjunct professor with the SFU School of Computing Science, Prof. Daniel Cohen-Or, is featured as the annual SIGGRAPH Achievement Award winner. Danny has been collaborating with Richard Zhang and students in the lab since 2008!
August 21, 2018
A special event honouring Professor Eugene Fiume, on the occasion of his 60-th birthday, was held at the SFU Harbour Center on August 17, right after SIGGRAPH 2018. Many of Eugene's first-generation PhDs from the University of Toronto attended the celebratory workshop and gave their account of fun and inspiring stories about what it was like to be his graduate students. Eugene's computer graphics instructor during his undergraduate years at the University of Waterloo provided hint of how Eugene was already "ahead of the class" then. The event featured Prof. Pat Hanrahan from Stanford University, as the keynote speaker. Pat spoke of "theory vs. practice" to highlight how over the years, Eugene has been among the rare group of people in computer graphics, who have emphasized the importance of theory in the field.
July 22, 2018
Congratulations to all SFU researchers that were able to have an impressive count of 12 papers accepted at the European Conference on Computer Vision 2018 (ECCV 2018)! ECCV is considered, together with ICCV and CVPR, one of the top level conferences in computer vision. Here is the full list of accepted papers with SFU co-authors:
●"Hierarchical Relational Networks for Group Activity Recognition and Retrieval" by Mostafa Ibrahim*, Simon Fraser University; Greg Mori, Simon Fraser University;
●"Neural Procedural Reconstruction for Residential Buildings" by Huayi Zeng*, Washington University in St.Louis; Jiaye Wu, Washington University in St.Louis; Yasutaka Furukawa, Simon Fraser University;
●"IM2Hand3D: Leveraging Multi-task Network for 3D Hand Pose Estimation from a Color Image" by Xiaoming Deng*, Chinese Academy of Sciences; Wenyong Zheng, Chinese Academy of Sciences ; Yinda Zhang, Princeton University; Jian Shi, Chinese Academy of Sciences ; Ping Tan, Simon Fraser University; Liang Chang, Beijing Normal University; Yuying Zhu, Chinese Academy of Sciences;
●"FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans" by Chen Liu*, Washington University in St. Louis; Jiaye Wu, Washington University in St.Louis; Yasutaka Furukawa, Simon Fraser University;
●"Probabilistic Video Generation using Holistic Attribute Control" by Jiawei He*, Simon Fraser University; Andreas Lehrmann, Facebook; Joe Marino, California Institute of Technology; Greg Mori, Simon Fraser University; Leonid Sigal, University of British Columbia;
●"Constraints Matter in Deep Neural Network Compression" by Changan Chen, Simon Fraser University; Fred Tung*, Simon Fraser University; Naveen Vedula, Simon Fraser University; Greg Mori, Simon Fraser University;
●"Characterize Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation" by CHAOWEI XIAO, University of Michigan, Ann Arbor; Ruizhi Deng, Simon Fraser University; Bo Li*, University of Illinois at Urbana Champaign; Fisher Yu, UC Berkeley; mingyan liu, university of Michigan, Ann Arbor; Dawn Song, UC Berkeley;
●"Faces as Lighting Probes via Unsupervised Deep Highlight Extraction" by Renjiao Yi*, Simon Fraser University; Chenyang Zhu, Simon Fraser University; Ping Tan, Simon Fraser University; Stephen Lin, Microsoft Research;
●"Sparsely Aggregated Convolutional Networks" by Ligeng Zhu*, Simon Fraser University; Ruizhi Deng, Simon Fraser University; Michael Maire, Toyota Technological Institute at Chicago; Zhiwei Deng, Simon Fraser University; Greg Mori, Simon Fraser University; Ping Tan, Simon Fraser University;
●"RIDI: Robust IMU Double Integration" by Hang Yan*, Washington University in St. Louis; Qi Shan, Zillow Group; Yasutaka Furukawa, Simon Fraser University;
●"Object Level Visual Reasoning in Videos" by Fabien Baradel, LIRIS; Natalia Neverova*, Facebook AI Research; Christian Wolf, INSA Lyon, France; Julien Mille, INSA Centre Val de Loire; Greg Mori, Simon Fraser University.
●"SketchyScene: Richly-Annotated Scene Sketches" by Changqing Zou*, University of Maryland (UMD); Qian Yu, Queen Mary University of London; Ruofei Du, UMD; Haoran Mo, sun yat sen university; Yi-Zhe Song, Queen Mary University of London; Tao Xiang, Queen Mary, University of London, UK; Chengying Gao, sun yat sen university; Baoquan Chen, Shandong University; Hao Zhang, SFU.
