Yi-Ruei Liu 劉珆睿
Incoming Ph.D student @ NYCU CS
About Me
I’m an incoming Ph.D. student in Computer Science at National Yang Ming Chiao Tung University (NYCU), advised by Prof. Yu-Lun Liu. I work on 3D scene reconstruction and physically-based rendering, particularly focusing on inverse rendering, 3D Gaussian Splatting, and physics effect simulation.
I received my Master of Computer Science from the University of Illinois Urbana-Champaign (UIUC), and bachelor in Computer Science from NYCU.
I am always open to research collaborations. If you are interested in exploring potential projects together, please feel free to get in touch.
News
| Dec 22, 2025 | Graduated from UIUC with a MCS degree. |
|---|---|
| Dec 07, 2025 | Delivered an oral presentation on 4D-GRT at the NeurIPS 2025 SpaVLE workshop. |
| Sep 23, 2025 | 4D-GRT accepted to NeurIPS 2025 SpaVLE workshop as an Oral Paper. |
| Jul 01, 2025 | Joined Academia Sinica AIIU Lab as a Research Assistant, supervised by Prof. Jun-Cheng Chen. |
| Mar 20, 2025 | SpectroMotion accepted to CVPR 2025. |
| Jan 20, 2025 | Graduated from NYCU with a B.S. in Computer Science. |
| Sep 01, 2024 | Started my Master of Computer Science (MCS) degree at the UIUC. |
Publications
-
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite ImageryarXiv, 2025We present Skyfall-GS, a framework that synthesizes photorealistic, city-block scale 3D urban scenes from satellite imagery using diffusion models, eliminating the need for expensive 3D scanning and manual annotation while enabling real-time exploration.
-
Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data GenerationNeurIPS 2025 SpaVLE workshop, 2025We present 4D-GRT, a 4D Gaussian Splatting framework that generates physically accurate camera effects in dynamic scenes via differentiable ray tracing. Our approach combines a two-stage reconstruction pipeline with ray tracing to simulate complex optical effects, providing a robust foundation for camera-aware data generation.
-
SpectroMotion: Dynamic 3D Reconstruction of Specular ScenesIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025We present SpectroMotion, the first 3D Gaussian Splatting method capable of reconstructing photorealistic dynamic specular scenes. By combining 3DGS with physically-based rendering and deformation fields, we achieve high-quality synthesis of challenging real-world dynamic reflective surfaces.