Visual computing researchers receive multiple awards at CVPR
Visual computing researchers from SFU received multiple awards at the annual Conference on Computer Vision and Pattern Recognition (CVPR) this past week. CVPR is the premier conference in computer vision with the highest impact factor among all conferences in computer science and was held virtually for the first time this year from June 14-19. Computing science professor Greg Mori served as one of four program chairs at the conference.
First-year PhD student Zhiqin Chen, his supervisor professor Richard Zhang, together with computing science alumnus Andrea Tagliasacchi (a senior research scientist at Google) won the Best Student Paper Award. Their paper “BSP-Net: Generating Compact Meshes via Binary Space Partitioning” introduces a deep neural network which applies a classical graphics technique to learn compact shape representations. The network directly outputs polygonal meshes, which are the dominant representation of 3D shapes in many applications. The award was one of three best paper awards given out of a total of 6,424 submissions, chosen by an external panel of expert researchers in the field.
Professor Yasutaka Furukawa won the PAMI Longuet-Higgins Prize for his contributions to 3D dense reconstruction. The prize recognizes CVPR papers from ten years ago that have had a significant impact on computer vision research. Professor Furukawa wrote a milestone paper on “multi-view stereo reconstruction” for CVPR 2007, which has been cited more than 3,000 times. His software has been used by Google, Lucas Film, Weta Digital and Maxon, as well as hundreds of non-profit outfits, particularly for cultural heritage preservation.
"I am incredibly proud of the achievements by our colleagues," says Mori. "These major awards in a top conference are a testament to the caliber of research performed at SFU."
“Visual computing has been the fastest growing research cluster at the School of Computing Science in recent years,” says Zhang. “Since 2014, faculty count in the GrUVi and Vision and Media labs has more than tripled! Our excellent hires from top institutions such as Berkeley, Stanford, and ETH, have helped attract top talented graduate students and postdocs across the globe and offered strong support to our unique Professional Master’s Program. The success at CVPR this year is a result of the vision and growth strategy implemented by the school.”
SFU’s School of Computing Science boasts one of the strongest Computer Vision and Graphics research groups in the world according to CS Rankings. Besides the role of a program chair and two prestigious awards, the group contributed 11 technical papers (5 oral presentations), 3 invited talks, 4 co-organized workshops, and one Best Paper Award at one of the workshops.