From June 18th through 22nd some of the top researchers working in computer vision will gather virtually and in-person in Vancouver for IEEE/CVF’s annual international conference on Computer Vision and Pattern Recognition (CVPR). This hybrid conference will include talks, workshops, short courses, and an expo, making it the perfect setting for academics, students, and industry representatives to share innovative information and make high quality connections.
CAIDA has 4 members who have had a total of 9 papers accepted for CVPR 2023. An additional 11 UBC researchers have had papers accepted for CVPR this year, totalling a representation of 15 individuals from UBC across 11 different papers. This is an extraordinary accomplishment and each researcher deserves a huge congratulations. You can see a list of all accepted papers represented by UBC members below, with the CAIDA members bolded and featuring a link to their webpages. A full list of CVPR 2023 accepted papers can be found here, and you can learn more about this year’s conference here.
Yichen Guo () · Mai Xu (Beihang University, Tsinghua University) · Lai Jiang (University of British Columbia) · Leonid Sigal (University Of British Columbia) · Yunjin Chen (Alibaba Group)
DINN360: Deformable Invertible Neural Network for Latitude-Aware 360° Image Rescaling
Xingzhe He (None) · Gaurav Bharaj (Flawless AI) · David Ferman (Flawless AI) · Helge Rhodin (UBC) · Pablo Garrido (Flawless AI)
Few-Shot Geometry-Aware Keypoint Localization
Kacper Kania (Warsaw University of Technology) · Stephan J. Garbin (Microsoft) · Andrea Tagliasacchi (Simon Fraser University, Google Brain) · Virginia Estellers (Microsoft) · Kwang Moo Yi (University Of British Columbia) · Julien Valentin (Microsoft) · Tomasz Trzciński (Jagiellonian University) · Marek Kowalski (Microsoft)
BlendFields: Few-Shot Example-Driven Facial Modeling
Aimon Rahman (None) · Jeya Maria Jose Valanarasu (Johns Hopkins University) · Ilker Hacihaliloglu (University of British Columbia) · Vishal M. Patel (Johns Hopkins University)
Ambiguous Medical Image Segmentation Using Diffusion Models
Tanzila Rahman (University of British Columbia) · Hsin-Ying Lee (Snap Inc.) · Jian Ren (Snap Inc.) · Sergey Tulyakov (Snap Inc.) · Shweta Mahajan (University of British Columbia) · Leonid Sigal (University Of British Columbia)
Make-a-Story: Visual Memory Conditioned Consistent Story Generation
Ramin Nakhli (University of British Columbia) · Puria Azadi Moghadam (University of British Columbia) · Haoyang Mi (Johns Hopkins School of Medicine) · Hossein Farahani (University of British Columbia) · Alexander Baras (Johns Hopkins University) · Blake Gilks (University of British Columbia) · Ali Bashashati (University of British Columbia)
Sparse Multi-Modal Graph Transformer With Shared-Context Processing for Representation Learning of Giga-Pixel Images
Anurag Ranjan (Apple) · Kwang Moo Yi (University Of British Columbia) · Jen-Hao Rick Chang (Apple) · Oncel Tuzel (Apple)
FaceLit: Neural 3D Relightable Faces
Jen-Hao Rick Chang (Apple) · Wei-Yu Chen (Carnegie Mellon University) · Anurag Ranjan (Apple) · Kwang Moo Yi (University Of British Columbia) · Oncel Tuzel (Apple)
Pointersect: Neural Rendering With Cloud-Ray Intersection
Mohammed Suhail (University of British Columbia) · Erika Lu (Google) · Zhengqi Li (Google) · Noah Snavely (Google / Cornell) · Leonid Sigal (University Of British Columbia) · Forrester Cole (Google)
Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular
Zhijie Wu (None) · Yuhe Jin (University of British Columbia) · Kwang Moo Yi (University Of British Columbia)
Neural Fourier Filter Bank
Xitong Yang (Meta) · Fu-Jen Chu (Facebook) · Matt Feiszli (Meta AI) · Raghav Goyal (University of British Columbia) · Lorenzo Torresani (Facebook) · Du Tran (None)
Relational Space-Time Query in Long-Form
Note: All CAIDA Members have been bolded and a link has been provided to their personal webpages