BYLINE: IEEE Computer Society and Computer Vision Foundation
Newswise — Nashville, Tenn., 13 June 2025 – Today, IEEE Computer Society (CS) and the Computer Vision Foundation (CVF) announced the award-winning papers from the 2025 Computer Vision and Pattern Recognition (CVPR) Conference, as well as the recipients of this year’s AI Art awards. Both programs recognize outstanding achievements in computer vision.
Best Paper Awards
The papers awarded this year showcase significant advancements in the field of computer vision. Selected by the CVPR Awards Selection Committee based on unanimous agreement, these works underscore the remarkable innovation present at the conference.
Authors: Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, David Novotny
(Fri., 13 June, 2 p.m. – 2:15 p.m., Karl Dean Grand Ballroom)
The first awardee, representing a collaboration between the University of Oxford and Meta AI, introduced the Visual Geometry Grounded Transformer (VGGT), a groundbreaking feed-forward neural network. VGGT stands out by directly estimating critical 3D scene properties from hundreds of input views, surpassing traditional approaches in both speed and accuracy. The authors highlight the simplicity and efficiency of their method, making it particularly advantageous for real-time applications, which has been a challenge in optimization-based strategies.
Authors: Anagh Malik, Benjamin Attal, Andrew Xie, Matthew O’Toole, David B. Lindell
(Sat., 14 June, 10 a.m. – 10:15 a.m., Karl Dean Grand Ballroom)
The second awardee, a collaborative effort from the University of Toronto, Vector Institute, and Carnegie Mellon University, presented the first system for physically-based neural inverse rendering gleaned from videos taken from multiple viewpoints of light propagation. This innovative method models and inverts time-resolved measurements from a LiDAR system, allowing for the retrieval of scene geometry and the rendering of light movement in videos. The authors note its potential impact on fields such as autonomous navigation and remote sensing, especially in complex lighting situations.
“The CVPR program this year features many important papers that may have transformative impacts on the field,” explained Fuxin Li, CVPR 2025 Program Co-Chair and an associate professor at Oregon State University. “We congratulate these papers for standing out in an extremely strong lineup of award candidates. We would also like to thank the award committee for their hard work in making these choices.”
Best Paper Honorable Mentions
The conference also recognized several distinguished papers with honorable mention. Notably:
Authors: Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa, Aleksander Holynski, Noah Snavely
(Sat., 14 June, 9 a.m. – 9:15 a.m., Karl Dean Grand Ballroom)
Authors: Amir Bar, Gaoyue Zhou, Danny Tran, Trevor Darrell, Yann LeCun
(Sat., 14 June, 1:45 p.m. – 2 p.m., ExHall A2)
Additional honorable mentions were awarded to:
Authors: Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, among others
(Fri., 13 June, 9:45 a.m. – 10 a.m., ExHall A2)
Authors: Jialin Zhu, Jiangbei Yue, Feixiang He, He Wang
(Sun., 15 June, 10 a.m. – 10:15 a.m., Davidson Ballroom)
Also of note is the Best Student Paper Honorable Mention, awarded to:
Authors: Kaihang Pan, Wang Lin, Zhongqi Yue, with their team
(Sun., 15 June, 2:15 p.m. – 2:30 p.m., ExHall A2)
All award-winning papers are notable for their exceptional contributions to advancing computer vision and artificial intelligence. Their recognition was celebrated during the conference Welcome and Awards Ceremony, and they will be delivered as both oral presentations and posters over the course of the event.
As Phillip Isola, CVPR 2025 Program Co-Chair and an associate professor at MIT, remarked, “These papers represent some of the highest quality work at the conference, showcasing groundbreaking results and creative new ideas.”
AI Art Program Awardees
This year, the CVPR AI Art Program took center stage, diving deep into the intersection of science and artistry. The program encouraged explorations that incorporate computer vision techniques like generative models and object recognition. After evaluating over 100 submissions, the AI Art Award Winners were announced:
- Tom White, “Atlas of Perception“: This piece delves into the “visual vocabulary” of vision models, presenting a sculptural interpretation that investigates the latent space of neural networks and how machines interpret reality.
- Masaru Mizuochi, “Green Diffusion“: Highlighting the duality of “destruction” and “creation,” this work contrasts the decomposition processes of soil microorganisms with the operations of an AI diffusion model.
- Mingyong Cheng, Sophia Sun, Han Zhang, “Learning to Move, Learning to Play, Learning to Animate“: This cross-disciplinary performance combines self-developed robots, real-time AI generation, and unique audio synthesis methods to blur the lines between technology and artistry.
Each award winner was given a certificate and a cash prize, recognizing their innovative approach to melding AI with art.
“There’s such rich material in the space that connects AI and art,” commented AI Art Program Curator Luba Elliott. “This program encourages artists to continue exploring its potential.”
About CVPR 2025
The Computer Vision and Pattern Recognition Conference (CVPR) is recognized as the leading event in computer vision research, integral for advancements in artificial intelligence, machine learning, augmented reality, virtual reality, and more. Sponsored jointly by the IEEE Computer Society and the Computer Vision Foundation, CVPR serves as a crucial platform for discussing significant findings and future applications in these disciplines. Each year, more than 10,000 scientists and engineers attend, making it an exceptional venue for networking and knowledge-sharing.
This year’s conference, taking place from June 11-15 at the Music City Center in Nashville, Tenn., includes both in-person and virtual sessions. Those interested in more details about CVPR 2025 can visit cvpr.thecvf.com.
About the Computer Vision Foundation
The Computer Vision Foundation (CVF) is a non-profit organization committed to supporting research across all areas of computer vision. In conjunction with IEEE Computer Society, it co-sponsors major computer vision conferences, including CVPR and the International Conference on Computer Vision (ICCV). More information can be found at thecvf.com.
About the IEEE Computer Society
The IEEE Computer Society (CS) is the world’s largest professional organization for computing professionals, engaging individuals from various industries, academia, and scientific research. CS is dedicated to setting educational and professional standards that drive technological advancements. Through conferences, publications, and collaborative programs, it fosters discussions and partnerships that shape the future of the computing industry. For further information, visit computer.org.