2026-09-21T11:36:46Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/129543 2026-02-05 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01 The student, Ziyang Xie, accepted the attached license on 2025-04-28 at 12:37. The student, Ziyang Xie, submitted this Thesis for approval on 2025-04-28 at 12:45. This Thesis was approved for publication on 2025-04-28 at 16:02. DSpace SAF Submission Ingestion Package generated from Vireo submission #21829 on 2025-10-19 at 19:15:06 Build realistic and interactive 3D scene simulation from in-the-wild videos Xie, Ziyang 2025-04-28 Forsyth, David 3D Reconstruction 3D Simulation Gaussian Splatting eng This thesis proposes a unified system for constructing realistic and interactive 3D scene simulations directly from in-the-wild monocular videos. Given unstructured video input, the system reconstructs complete virtual environments that support high-fidelity rendering and real-time physical interaction. The pipeline is designed to enable a broad range of applications, including embodied agent training, sim-to-real transfer, and virtual content creation. The pipeline addresses key challenges in 3D scene simulation through four core components: (1) a geometry-consistent background reconstruction module that combines Structure-from-Motion, 3D Gaussian Splatting, and learned geometric priors to reconstruct consistent large-scale environments; (2) a tri-branch foreground object modeling framework that supports object-level reconstruction, retrieval from large-scale 3D asset databases, and generation via 3D generative models; (3) a scene composition, relighting and rendering module that ensures photorealistic composition of foreground and background with consistent placement, lighting and shadows; and (4) a simulation layer that enables realistic sensor simulation and interactive physics-based interaction within the simulation environment. A key feature of the system is its extensibility: each component is designed to incorporate future advances in neural rendering, generative modeling, and geometry reconstruction. This design enables the pipeline to serve both as a practical simulation pipeline and as a research platform for complex, real-world 3D scene simulation. By bridging unconstrained video input with high-fidelity interactive simulation, this work offers a scalable and generalizable framework for building realistic virtual environments from everyday video data. 2025-05 Thesis https://hdl.handle.net/2142/129543 Copyright 2025 Ziyang Xie Siebel School Comp & Data Sci Computer Science University of Illinois Urbana-Champaign M.S. Thesis