Linjie Lyu after successfully defending his thesis. Photo: MPI-INF/Bertram Somieski
On 16 January 2026 Linjie Lyu successfully defended his thesis with the title: "Global Illumination in Inverse Rendering: From Probabilistic Reconstruction to Generative Editing". He joined the Graduate School of Computer Science of Saarland University in October 2019 and MPI for Informatics as a doctoral candidate in June 2021. The thesis was supervised by Prof. Dr. Christian Theobalt, Scientific Director of the Department Visual Computing and Artificial Intelligence. The doctoral degree is awarded by Saarland University.
Abstract of the thesis:
Reconstructing geometry, materials, and lighting from images - known as inverse rendering - is a central problem in computer graphics and vision. A key difficulty lies in accurately modeling global illumination effects such as shadows, reflections, and color bleeding, which are essential for realistic scene understanding but challenging to infer from limited visual observations.
This thesis advances inverse rendering by explicitly accounting for global illumination while addressing two fundamental challenges: ambiguity in reconstructing 3D scenes from images, and the high computational cost of simulating light transport. To handle ambiguity, we introduce probabilistic inverse rendering frameworks that represent multiple plausible scene interpretations, enabling uncertainty-aware reconstruction and principled strategies for image acquisition. To improve efficiency, we develop differentiable rendering techniques that approximate complex light transport, including fast soft shadow computation and neural representations that enable efficient relighting under unknown illumination. In addition, we explore diffusion-based generative models as complementary priors for global-illumination-aware image decomposition and editing, enabling semantic manipulation of lighting and materials without full 3D reconstruction. Together, these contributions form a unified framework for scalable and robust inverse rendering in complex environments. By combining physical modeling, uncertainty reasoning, and generative priors, this work enables more reliable scene reconstruction and editing, with applications in 3D content creation, visual effects, and augmented reality.