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 #11 in the world in terms of top publications in visual computing, as of 7/2020) 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 several 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.
May 18, 2023
The recoding is available in this link (SFU account is needed).
Here is some information about the lecture.
Title:
Shading Languages and the Emergence of Programmable Graphics Systems
Abstract:
A major challenge in using computer graphics for movies and games is to create a rendering system that can create realistic pictures of a virtual world. The system must handle the variety and complexity of the shapes, materials, and lighting that combine to create what we see every day. The images must also be free of artifacts, emulate cameras to create depth of field and motion blur, and compose seamlessly with photographs of live action.
Pixar's RenderMan was created for this purpose, and has been widely used in feature film production. A key innovation in the system is to use a shading language to procedurally describe appearance. Shading languages were subsequently extended to run in real-time on graphics processing units (GPUs), and now shading languages are widely used in game engines. The final step was the realization that the GPU is a data-parallel computer, and the the shading language could be extended into a general-purpose data-parallel programming language. This enabled a wide variety of applications in high performance computing, such as physical simulation and machine learning, to be run on GPUs. Nowadays, GPUs are the fastest computers in the world. This talk will review the history of shading languages and GPUs, and discuss the broader implications for computing.
Biography:
Pat Hanrahan is the Canon Professor of Computer Science and Electrical Engineering in the Computer Graphics Laboratory at Stanford University. His research focuses on rendering algorithms, graphics systems, and visualization. Hanrahan received a Ph.D. in biophysics from the University of Wisconsin-Madison in 1985. As a founding employee at Pixar Animation Studios in the 1980s, Hanrahan led the design of the RenderMan Interface Specification and the RenderMan Shading Language. In 1989, he joined the faculty of Princeton University. In 1995, he moved to Stanford University. More recently, Hanrahan served as a co-founder and CTO of Tableau Software. He has received three Academy Awards for Science and Technology, the SIGGRAPH Computer Graphics Achievement Award, the SIGGRAPH Stephen A. Coons Award, and the IEEE Visualization Career Award. He is a member of the National Academy of Engineering and the American Academy of Arts and Sciences. In 2019, he received the ACM A. M. Turing Award.
May 18, 2023
The recoding is available in this link (SFU account is needed).Here is some information about the lecture.Title:Shading Languages and the Emergence of Programmable Graphics SystemsAbstract:A major challenge in using computer graphics for movies and games is to create a rendering system that can create realistic pictures of a virtual world. The system must handle the variety and complexity of the shapes, materials, and lighting that combine to create what we see every day. The images must also be free of artifacts, emulate cameras to create depth of field and motion blur, and compose seamlessly with photographs of live action.Pixar's RenderMan was created for this purpose, and has been widely used in feature film production. A key innovation in the system is to use a shading language to procedurally describe appearance. Shading languages were subsequently extended to run in real-time on graphics processing units (GPUs), and now shading languages are widely used in game engines. The final step was the realization that the GPU is a data-parallel computer, and the the shading language could be extended into a general-purpose data-parallel programming language. This enabled a wide variety of applications in high performance computing, such as physical simulation and machine learning, to be run on GPUs. Nowadays, GPUs are the fastest computers in the world. This talk will review the history of shading languages and GPUs, and discuss the broader implications for computing.Biography:Pat Hanrahan is the Canon Professor of Computer Science and Electrical Engineering in the Computer Graphics Laboratory at Stanford University. His research focuses on rendering algorithms, graphics systems, and visualization. Hanrahan received a Ph.D. in biophysics from the University of Wisconsin-Madison in 1985. As a founding employee at Pixar Animation Studios in the 1980s, Hanrahan led the design of the RenderMan Interface Specification and the RenderMan Shading Language. In 1989, he joined the faculty of Princeton University. In 1995, he moved to Stanford University. More recently, Hanrahan served as a co-founder and CTO of Tableau Software. He has received three Academy Awards for Science and Technology, the SIGGRAPH Computer Graphics Achievement Award, the SIGGRAPH Stephen A. Coons Award, and the IEEE Visualization Career Award. He is a member of the National Academy of Engineering and the American Academy of Arts and Sciences. In 2019, he received the ACM A. M. Turing Award.
May 15, 2023
We are thrilled to share that Prof. Andrea Tagliasacchi will serve as co-chair for the International Conference on 3D Vision (3DV) 2024, alongside Prof. Siyu Tang from ETH and Federico Tombari from Google. Smaller conferences like 3DV play a vital role in fostering lasting networks within the research community, and 3DV 2024 promises to be an exciting opportunity for this.
Furthermore, the call for papers for 3DV 2024 is now officially open. The conference will take place in the beautiful location of Davos, Switzerland, where World Economic Forum is annually held there. Researchers are encouraged to submit their papers by July 31st. For additional details, please visit the conference website at https://3dvconf.github.io/2024/call-for-papers/. Don't miss this incredible chance to share your research with the international community at 3DV 2024!
May 15, 2023
We are thrilled to share that Prof. Andrea Tagliasacchi will serve as co-chair for the International Conference on 3D Vision (3DV) 2024, alongside Prof. Siyu Tang from ETH and Federico Tombari from Google. Smaller conferences like 3DV play a vital role in fostering lasting networks within the research community, and 3DV 2024 promises to be an exciting opportunity for this. Furthermore, the call for papers for 3DV 2024 is now officially open. The conference will take place in the beautiful location of Davos, Switzerland, where World Economic Forum is annually held there. Researchers are encouraged to submit their papers by July 31st. For additional details, please visit the conference website at https://3dvconf.github.io/2024/call-for-papers/. Don't miss this incredible chance to share your research with the international community at 3DV 2024!
April 18, 2023
Record link is here
Title: Diffusion Models: From Foundations to Image, Video and 3D Content Creation
Abstract: Denoising diffusion-based generative models have led to multiple breakthroughs in deep generative learning. In this talk, I will provide an overview over recent works by the NVIDIA Toronto AI Lab on diffusion models and their applications for digital content creation. I will start with a short introduction of diffusion models and recapitulate their mathematical formulation. Then, I will briefly discuss our foundational works on diffusion models, which includes advanced diffusion processes for faster and smoother diffusion and denoising, techniques for more efficient model sampling, as well as latent space diffusion models, a flexible diffusion model framework that has been widely used in the literature. Moreover, I will discuss works that use diffusion models for image, video and 3D content creation. This includes large text-to-image models as well as recent work on high resolution video synthesis with latent diffusion models. I will also summarize some of our efforts on 3D generative modeling. This includes object-centric 3D synthesis by training diffusion models on geometric shape datasets or leveraging large-scale text-to-image diffusion models as priors for shape distillation, as well as full scene-level generation with hierarchical latent diffusion models.
Bio: Karsten Kreis is a senior research scientist at NVIDIA’s Toronto AI Lab. Prior to joining NVIDIA, he worked on deep generative modeling at D-Wave Systems and co-founded Variational AI, a startup utilizing generative models for drug discovery. Before switching to deep learning, Karsten did his M.Sc. in quantum information theory at the Max Planck Institute for the Science of Light and his Ph.D. in computational and statistical physics at the Max Planck Institute for Polymer Research. Currently, Karsten’s research focuses on developing novel generative learning methods and on applying deep generative models on problems in areas such as computer vision, graphics and digital artistry, as well as in the natural sciences.
April 18, 2023
Record link is hereTitle: Diffusion Models: From Foundations to Image, Video and 3D Content CreationAbstract: Denoising diffusion-based generative models have led to multiple breakthroughs in deep generative learning. In this talk, I will provide an overview over recent works by the NVIDIA Toronto AI Lab on diffusion models and their applications for digital content creation. I will start with a short introduction of diffusion models and recapitulate their mathematical formulation. Then, I will briefly discuss our foundational works on diffusion models, which includes advanced diffusion processes for faster and smoother diffusion and denoising, techniques for more efficient model sampling, as well as latent space diffusion models, a flexible diffusion model framework that has been widely used in the literature. Moreover, I will discuss works that use diffusion models for image, video and 3D content creation. This includes large text-to-image models as well as recent work on high resolution video synthesis with latent diffusion models. I will also summarize some of our efforts on 3D generative modeling. This includes object-centric 3D synthesis by training diffusion models on geometric shape datasets or leveraging large-scale text-to-image diffusion models as priors for shape distillation, as well as full scene-level generation with hierarchical latent diffusion models.Bio: Karsten Kreis is a senior research scientist at NVIDIA’s Toronto AI Lab. Prior to joining NVIDIA, he worked on deep generative modeling at D-Wave Systems and co-founded Variational AI, a startup utilizing generative models for drug discovery. Before switching to deep learning, Karsten did his M.Sc. in quantum information theory at the Max Planck Institute for the Science of Light and his Ph.D. in computational and statistical physics at the Max Planck Institute for Polymer Research. Currently, Karsten’s research focuses on developing novel generative learning methods and on applying deep generative models on problems in areas such as computer vision, graphics and digital artistry, as well as in the natural sciences.
March 8, 2023
We are thrilled to announce that Professor Yasutaka Furukawa, one of our esteemed professors, has been appointed as the Program Chair for the International Conference on Computer Vision (ICCV) 2023. The ICCV, a top-tier event in the field of computer vision, provides an excellent platform to exchange novel ideas and discuss the latest advancements. We invite you to learn more about the ICCV 2023 and Prof. Furukawa's role by visiting the official conference website at https://iccv2023.thecvf.com/.
March 8, 2023
We are thrilled to announce that Professor Yasutaka Furukawa, one of our esteemed professors, has been appointed as the Program Chair for the International Conference on Computer Vision (ICCV) 2023. The ICCV, a top-tier event in the field of computer vision, provides an excellent platform to exchange novel ideas and discuss the latest advancements. We invite you to learn more about the ICCV 2023 and Prof. Furukawa's role by visiting the official conference website at https://iccv2023.thecvf.com/.
Aug 7th, 2022
The first SFU Visual Computing Workshop was held on Aug 7th at the Morris J. Wosk Centre for Dialogue in Vancouver, Canada. This workshop preceded SIGGRAPH 2022, so it was conceived as a warmup for the researchers that were gathering for the most prestigious Computer Graphics conference.
The workshop was organized by Daniel Cohen-Or, Richard Zhang, Ali Mahdavi-Amiri, and Wallace Lira. The event featured some of the leading voices and rising stars in the Computer Graphics community, where the panelists included Angel Chang, Yasutaka Furukawa, Rana Hanocka, Niloy Mitra, and Ariel Shamir. Further, the featured speakers were Amit Bermano, Jason Peng, Rana Hanocka, Niloy Mitra, Ming Lin, Yifan Wang, and Andrea Tagliasacchi.
Aug 7th, 2022
The first SFU Visual Computing Workshop was held on Aug 7th at the Morris J. Wosk Centre for Dialogue in Vancouver, Canada. This workshop preceded SIGGRAPH 2022, so it was conceived as a warmup for the researchers that were gathering for the most prestigious Computer Graphics conference.The workshop was organized by Daniel Cohen-Or, Richard Zhang, Ali Mahdavi-Amiri, and Wallace Lira. The event featured some of the leading voices and rising stars in the Computer Graphics community, where the panelists included Angel Chang, Yasutaka Furukawa, Rana Hanocka, Niloy Mitra, and Ariel Shamir. Further, the featured speakers were Amit Bermano, Jason Peng, Rana Hanocka, Niloy Mitra, Ming Lin, Yifan Wang, and Andrea Tagliasacchi.
May 4th, 2022
Congratulations to Hao (Richard) Zhang and Manolis Savva for receiving awards at the Graphics Interface 2022. Richard has received the 2022 CHCCS/SCDHM Achievement Award of the Canadian Human-Computer Communications Society. Richard has had numerous high-impact contributions to computer graphics including geometric modeling, shape analysis, geometric deep learning, and computational design and fabrication. Manolis has received the 2022 Early Career Researcher Award. Manolis has established himself as a central figure in topics at the intersection of computer graphics, 3D sensing, and machine learning. To learn more about the research contributions of Richard and Manolis please checkout here and here.
May 4th, 2022
Congratulations to Hao (Richard) Zhang and Manolis Savva for receiving awards at the Graphics Interface 2022. Richard has received the 2022 CHCCS/SCDHM Achievement Award of the Canadian Human-Computer Communications Society. Richard has had numerous high-impact contributions to computer graphics including geometric modeling, shape analysis, geometric deep learning, and computational design and fabrication. Manolis has received the 2022 Early Career Researcher Award. Manolis has established himself as a central figure in topics at the intersection of computer graphics, 3D sensing, and machine learning. To learn more about the research contributions of Richard and Manolis please checkout here and here.
April 1, 2023
We are delighted to announce the establishment of the Visual and Interactive Computing Institute (VINCI), co-directed by our esteemed Prof. Yasutaka Furukawa and Prof. Parmit Chilana. VINCI has been brought to life by 44 dedicated faculty members from 14 different departments and 7 distinct faculties within SFU. The primary objective of the institute is to bolster interdisciplinary research collaborations.
February 27, 2023
Congratulations to all Gruviers who are publishing their work at CVPR 2023. Among the accepted papers, MobileNeRF is one of the 12 finalists for best paper award! Congrats for Zhiqin and Andrea for their excellent work!
CVPR is the premier conference on computer vision and will be held in Vancourver this year. To learn more about the sample work that Gruvi will be presenting checkout our publication page to get more information.
Sep 14th, 2022
Congratulations to Qimin Chen, Wallace Lira, and Sonia Raychaudhuri! They were selected as recipients for the inaugural CS Outstanding Teaching Assistent Award.
This award recognizes exceptional TAs in the School of Computing Science for their outstanding work in teaching and performing other TA duties. The recipients will be acknowledged at the October 20th school meeting.
May 5th, 2022
Title: MyStyle: A Personalized Generative Prior
Time: Friday, May 6th at 11:00 AM PST
Abstract: Deep generative models have proved to be successful for many image-to-image applications. Such models hallucinate information based on their large and diverse training datasets. Therefore, when enhancing or editing a portrait image, the model produces a generic and plausible output, but often it isn't the person who actually appears in the image. In this talk, I'll present our latest work, MyStyle - which introduces the notion of a personalized generative model. Trained on ~100 images of the same individual, MyStyle learns a personalized prior, custom to their unique appearance. This prior is then leveraged to solve ill-posed image enhancement and editing tasks - such as super-resolution, inpainting and changing the head pose.
March 2nd, 2022
Congratulations to all Gruviers who are publishing their work at CVPR 2022. CVPR is the premier conference on computer vision and will be held in New Orleans this year. To learn more about the sample work that Gruvi will be presenting checkout here and here.
Dec 20th, 2021
We wrap-up the year 2021 with great achievements and look forward to the new year ahead of us. In 2021, Gruviers were able to publish their work at many 1st tier conferences: CVPR (12 papers), SIGGRAPH and SIGGRAPH Asia (4 papers), ICCV (4 papers), Eurographics and Neurips. Congratulations to all Gruviers for their hard work.
Oct 19, 2021
Title: SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization
Time: Wednesday, Nov 3, 1:30 PM
Abstract: Multilayer-perceptrons (MLP) are known to struggle with learning functions of high-frequencies, and in particular cases with wide frequency bands. We present a spatially adaptive progressive encoding (SAPE) scheme for input signals of MLP networks, which enables them to better fit a wide range of frequencies without sacrificing training stability or requiring any domain specific preprocessing. SAPE gradually unmasks signal components with increasing frequencies as a function of time and space. The progressive exposure of frequencies is monitored by a feedback loop throughout the neural optimization process, allowing changes to propagate at different rates among local spatial portions of the signal space. We demonstrate the advantage of SAPE on a variety of domains and applications, including regression of low dimensional signals and images, representation learning of occupancy networks, and a geometric task of mesh transfer between 3D shapes.
September 24th, 2021
Congratulations to Zhiqin Chen for receiving a PhD Fellowship from Google. The Google PhD Fellowship Program was created to recognize outstanding graduate students doing exceptional and innovative research in areas relevant to computer science and related fields. Fellowships support promising PhD candidates of all backgrounds who seek to influence the future of technology. To learn more about Zhiqin's research please visit here.
