LOS ALAMITOS, Calif., 28 June 2023 – As the preeminent event for research and development in computer vision, artificial intelligence (AI), machine learning (ML), augmented and virtual reality (AR/VR), deep learning, and much more, the Computer Vision and Pattern Recognition (CVPR) Conference annually reveals the latest evolution of the field. This year, the conference, which took place 18-22 June in Vancouver, B.C., Canada, unveiled five key trends shaping the evolution of the community:

1. Render the real. Research emphasis this year was on bringing technology closer to reality. Top paper categories included 3D computer vision; image and video generation; and understanding humans in video.
2. Create an autonomous ecosystem. With advances in autonomous vehicles making their operation more consistent, research attention turned to ways to address the external influences that will impact them. In short, research is shifting from how the vehicle may react in an environment to planning for how the environment may respond to it.
3. Converge image and language for more sophisticated techniques. One needs to look no further than the latest artificial intelligence (AI) news to see how the technology is expanding from an image or text-based approach to a combined effort. Yet converging these modalities with accuracy creates complicated research challenges. A number of highlighted papers at CVPR turned their attention to these issues.
4. Collaborate to meet market demand. Throughout the conference, there was a focus on collaboration, including cross-disciplinary, as discussed in the panel presentation, “Scientific Discovery and the Environment,” and industry-academic as called out in the panel discussion, “History and Future of Artificial Intelligence and Computer Vision” and many other discussions. These discussions result in more widespread collaboration between academia, government, and industry to meet growing technological demands.
5. Embrace diversity and inclusion to combat bias. Both from a technical standpoint (bias mitigation and fair representation) and an inclusiveness perspective (different perspectives and vantage points contributing to new ideas), diversity and inclusion are critical to computer vision developments. The IEEE Computer Society (CS), the Computer Vision Foundation (CVF) and the IEEE CS Technical Community on Pattern Analysis and Machine Intelligence (TCPAMI) collectively put forward $300,000 USD for registration and travel grants aimed at drawing in a widely diverse community for this very reason.

“CVPR has been the premier outlet for research in computer vision and closely related fields for many years, and CVPR23 lived up to this tradition of excellence,” said Ramin Zabih, founder and president, CVF, conference co-sponsor. “At CVPR23 we saw significant advances both in pure research, which is pursued simply for the joy of discovery, as well as in applications that are poised to have a substantial impact on society.”

In addition, this year’s exhibitors and sponsors offered new developments at the event. From their contributions to the technical program and award-winning papers, to new product announcements and offerings, this year’s event featured deep insights from the corporate community.

“Exhibitors and sponsors brought with them fresh thinking, new developments and interesting insights,” said IEEE CS President Nita Patel, co-sponsor of CVPR 2023. “What really struck me is just how many new ideas took shape from discussions in the exhibit hall, at networking events, and following presentations. We look forward to seeing how these ideas have evolved when we convene for CVPR 2024.”

CVPR 2024 will take place in Seattle, Wash., U.S.A., 16 – 21 June.

For more information, download the infographic, “CVPR 2023 Reveals Top Five Computer Vision Trends,” or visit https://cvpr2023.thecvf.com/.

About CVPR 2023

The Computer Vision and Pattern Recognition Conference (CVPR) is the preeminent computer vision event for new research in support of artificial intelligence (AI), machine learning (ML), augmented and virtual reality (AR/VR), deep learning, and much more. Sponsored by the IEEE Computer Society (CS) and the Computer Vision Foundation (CVF), CVPR delivers the important advances in all areas of computer vision and pattern recognition and the various fields and industries they impact. With first-in-class technical content, a main program, tutorials, workshops, a leading-edge expo, and attended by more than 10,000 people annually, CVPR creates a one-of-a-kind opportunity for networking, recruiting, inspiration, and motivation.

CVPR 2023 took place 18-22 June at the Vancouver Convention Center in Vancouver, Canada, and virtually. For more information about CVPR 2023, visit https://cvpr2023.thecvf.com/.

About the Computer Vision Foundation

The Computer Vision Foundation (CVF) is a non-profit organization whose purpose is to foster and support research on all aspects of computer vision. Together with the IEEE Computer Society, it co-sponsors the two largest computer vision conferences, CVPR and the International Conference on Computer Vision (ICCV). Visit https://www.thecvf.com/ for more information.

About the IEEE Computer Society

Engaging computer engineers, scientists, academia, and industry professionals from all areas of computing, the IEEE Computer Society (CS) sets the standard for the education and engagement that fuels continued global technological advancement. Through conferences, publications, and programs, and by bringing together computer science and engineering leaders at every phase of their career for dialogue, debate, and collaboration, IEEE CS empowers, shapes, and guides the future of not only its members, but the greater industry, enabling new opportunities to better serve our world. Visit computer.org for more information.