Skip to yearly menu bar Skip to main content


Best Papers at CVPR Reveal New Results with Neural Networks for Real-Time Applications and Novel Ways to Manipulate Light for Scene Recovery

AI in Art Program announces award-winning works

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

Determined through the unanimous agreement of the CVPR Awards Selection Committee, the following papers were selected as this year’s award honorees:

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)

Engineers from the University of Oxford and Meta AI present Visual Geometry Grounded Transformer (VGGT), a feed-forward neural network that can directly estimate all key 3D scene properties for hundreds of input views, outperforming standard approaches. The paper concludes, “The simplicity and efficiency of our approach make it well-suited for real-time applications, which is another benefit over optimization-based approaches.

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)

A team from the University of Toronto, Vector Institute, and Carnegie Mellon University present the first system for physically based neural inverse rendering from multi-viewpoint videos of propagating light. The work models and inverts multi-viewpoint, time-resolved measurements of propagating light from a LiDAR system to recover scene geometry and to render videos of propagating light. As the paper sums up, this work, “has potential for impact in areas such as autonomous navigation or remote sensing — especially in scenarios with strong indirect lighting effects.”

“The CVPR program this year features many important papers that may have transformative impacts to the field,” said Fuxin Li, CVPR 2025 Program Co-Chair, and an associate professor at Oregon State University in Corvallis, Ore., U.S. “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

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) 

Authors: Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi, Niklas Muennighoff, Kyle Lo, Luca Soldaini, Jiasen Lu, Taira Anderson, Erin Bransom, Kiana Ehsani, Huong Ngo, YenSung Chen, Ajay Patel, Mark Yatskar, Chris Callison-Burch, Andrew Head, Rose Hendrix, Favyen Bastani, Eli VanderBilt, Nathan Lambert, Yvonne Chou, Arnavi Chheda, Jenna Sparks, Sam Skjonsberg, Michael Schmitz, Aaron Sarnat, Byron Bischoff, Pete Walsh, Chris Newell, Piper Wolters, Tanmay Gupta, Kuo-Hao Zeng, Jon Borchardt, Dirk Groeneveld, Crystal Nam, Sophie Lebrecht, Caitlin Wittlif, Carissa Schoenick, Oscar Michel, Ranjay Krishna, Luca Weihs, Noah A. Smith, Hannaneh Hajishirzi, Ross Girshick, Ali Farhadi, Aniruddha Kembhavi

(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)

Best Student Paper Honorable Mention

Authors: Kaihang Pan, Wang Lin, Zhongqi Yue, Tenglong Ao, Liyu Jia, Wei Zhao, Juncheng Li, Siliang Tang, Hanwang Zhang

(Sun., 15 June, 2:15 p.m. – 2:30 p.m., ExHall A2)

All award-winning papers demonstrate exceptional results that help to advance computer vision, artificial intelligence (AI), and more. They were announced during the conference Welcome and Awards Ceremony this morning. Each honored paper will be delivered as an oral presentation and a poster over the remaining days of the conference.

"These papers represent some of the highest quality work at the conference," said Phillip Isola, CVPR 2025 Program Co-Chair and an associate professor at the Massachusetts Institute of Technology (MIT) in Boston, Mass., U.S. "These papers include breakthrough results, important tools of broad interest, and creative new ideas."

AI Art Program Awardees

In addition to technical research, the CVPR AI Art Program explored the intersection of science and art and welcomed works that use or look at computer vision, including techniques such as generative models and  object and facial recognition. Selected from more than 100 accepted works, the AI Art Award Winners also were announced today and include:

  • Tom White, "Atlas of Perception” illuminates the "visual vocabulary" of vision models by exploring the latent space of neural networks. The sculptural representation examines how machines parse the world, providing insight into the grammar of appearance itself—the modular semantics of vision.
  • Masaru Mizuochi, “Green Diffusion” highlights the simultaneity of “destruction” and “creation” by juxtaposing the process of decomposition by soil microorganisms—turning material into fertile nutrients—with the noise-adding and noise-removing process of an AI diffusion model.
  • Mingyong Cheng, Sophia Sun, Han Zhang, “Learning to Move, Learning to Play, Learning to Animate” provides a cross-disciplinary multimedia performance piece featuring self-developed found material robots, real-time AI generation, motion tracking, audio spatialization, and bio-feedback-based audio synthesis.

Each winner received an award certificate and cash prize.

“There’s such rich material in the space that connects AI and art, and this program encourages artists to continue exploring its potential,” said AI Art Program Curator Luba Elliott. “Congratulations to this year’s winners and to all of our participants for their thoughtful takes on today’s landscape.”

About CVPR 2025

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, virtual and mixed reality (AR/VR/MR), 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 a first-in-class technical program, including tutorials and workshops, a leading-edge expo, and robust networking opportunities, CVPR, which is annually attended by more than 10,000 scientists and engineers, creates a one-of-a-kind opportunity for networking, recruiting, inspiration, and motivation.

CVPR 2025 is taking place 11-15 June at Music City Center in Nashville, Tenn., U.S., and participants may also access sessions virtually. For more information about CVPR 2025, visit cvpr.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 thecvf.com for more information.

About the IEEE Computer Society

Engaging computer engineers, scientists, academia, and industry professionals from all areas and levels of computing, the IEEE Computer Society (CS) serves as the world’s largest and most established professional organization of its type. IEEE CS sets the standard for the education and engagement that fuels continued global technological advancement. Through conferences, publications, and programs that inspire dialogue, debate, and collaboration, IEEE CS empowers, shapes, and guides the future of not only its 375,000+ community members, but the greater industry, enabling new opportunities to better serve our world. Visit computer.org for more information.