2026-09-21T02:05:51Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/129198 2025-10-20 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms The student, David Yao, accepted the attached license on 2025-04-13 at 23:59. The student, David Yao, submitted this Thesis for approval on 2025-04-14 at 00:06. This Thesis was approved for publication on 2025-04-15 at 05:27. DSpace SAF Submission Ingestion Package generated from Vireo submission #21758 on 2025-10-19 at 18:09:21 Uni4D: Unifying visual foundation models for 4D modeling from a single video Yao, David Yifan 2025-04-15 Wang, Shenlong Computer Vision Machine Learning Structure from Motion 4D Reconstruction Dynamic Modeling Video Depth Estimation Pose Estimation eng This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding. 2025-05 Thesis https://hdl.handle.net/2142/129198 Copyright 2025 David Yifan Yao Siebel School Comp & Data Sci Computer Science University of Illinois Urbana-Champaign M.S. Thesis