School of Information Sciences

Cao and Liu receive Best Paper Award for FreeOrbit4D

Wei Cao
Wei Cao
Yaoyao Liu 2026
Yaoyao Liu, Assistant Professor

PhD student Wei Cao and Assistant Professor Yaoyao Liu received a Best Paper Award at the 4th Workshop on Generative Models for Computer Vision, which was held during the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). The paper, "FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction," was co-authored with collaborators from the University of Illinois Urbana-Champaign, the University of Pennsylvania, and Eyeline Labs.

According to the researchers, FreeOrbit4D addresses a challenging problem in visual computing: how to transform an ordinary single-camera video into a new video of the same dynamic scene viewed from a user-specified camera path. This capability could make free-viewpoint replay, cinematic camera movement, and "bullet-time" effects possible without the expensive multi-camera studio setups typically required for such results. The team's method builds a 4D representation of a scene, capturing both its 3D structure and how it changes over time. 

"By separating the moving foreground from the background and reconstructing portions of the foreground object that were not visible in the original video, FreeOrbit4D provides stronger geometric guidance for video generation," said Cao. "This allows the system to produce videos that remain visually faithful and temporally consistent, even when the virtual camera moves far away from the original viewpoint."

The paper has been accepted to ACM SIGGRAPH 2026, one of the premier international conferences in computer graphics and interactive techniques. 

Led by Liu, the Computer Vision and Machine Learning Group studies a wide range of problems in visual understanding, data-efficient learning, and intelligent perception. The group's research lies at the intersection of computer vision and machine learning, with a special focus on building intelligent visual systems that are continual and data efficient.

Updated on
Backto the news archive

Related News

Wang group receives ICWSM Best Dataset Paper Award

A paper from Professor Dong Wang's Social Sensing & Intelligence Lab received the Best Dataset Paper Award at the International AAAI Conference on Web and Social Media (ICWSM) held in May 2026 in Los Angeles, California. According to Wang, the paper was accepted in the first review round, which had an acceptance rate of 4.7 percent (14 of 298 submissions). 

Adler and Wang to present at RESPECT 2026

Associate Professor Rachel Adler and Informatics PhD student Olive Wang will present their work at the Association for Computing Machinery Special Interest Group on Computer Science Education Conference on Research on Equity and Sustained Participation in Engineering, Computing, and Technology (RESPECT), which will be held in Chicago this week.

Bashir group presents work at PEPR 2026

PhD students Ramazan Yener, Eryue Xu, and Mubarak Raji presented their research this week at the 2026 USENIX Conference on Privacy Engineering Practice and Respect (PEPR) in Santa Clara, California. PEPR is focused on designing and building products and systems with privacy and respect for their users and the societies in which they operate. The students received USENIX grants covering their conference registration and providing travel support to attend the conference. 

Bashir group PEPR 2026

2025 Downs Intellectual Freedom Award given to Nicole A. Cooke

Nicole A. Cooke has been named the 2025 recipient of the Downs Intellectual Freedom Award for her advocacy, groundbreaking research, and dedication to diversity, equity, and inclusion within the field of library and information science. Cooke is the Augusta Baker Endowed Chair and professor in the College of Information and Communications at the University of South Carolina.

Nicole Cooke

iSchool researchers to present work at CVPR Conference

Assistant Professors Ismini Lourentzou and Yaoyao Liu, along with students from their labs, will present their research at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), held in Denver, Colorado, from June 3–7. CVPR is the flagship annual meeting of IEEE/CVF and PAMI-TC, where researchers present their latest advances in computer vision, pattern recognition, machine learning, robotics, and artificial intelligence, both in theory and practice. 

School of Information Sciences

501 E. Daniel St.

MC-493

Champaign, IL

61820-6211

Voice: (217) 333-3280

Email: ischool@illinois.edu

Back to top