Xingchang Huang successfully defended his PhD thesis. Photo: Bertam Somieski/ MPI-INF
On 24 November 2025, Xingchang Huang successfully defended his PhD thesis with the title "Understanding noise correlations in generative models for graphics content generation and editing". He joined MPI for Informatics and Saarland University as a doctoral candidate in June 2020. The thesis was supervised by Prof. Dr. Hans-Peter Seidel, Scientific Director of the Computer Graphics department, and Gurprit Singh, head of the Sampling and Rendering group. The doctoral degree is awarded by Saarland University.
Abstract of the thesis:
Graphics content plays an essential role in our daily lives, spanning diverse media forms such as images, videos, textures, point patterns, and 3D objects. Despite their ubiquity, limited research has investigated how the concept of noise correlation across these varied representations can have an impact on controllable graphics generation and editing aligned with user intent.
This thesis explores how noise correlations can inform and simplify the process of generating and editing visual content. We focus in particular on the synthesis and editing of point patterns, images, and stereo videos. Our primary contributions lie in developing novel pipelines that leverage noise correlations to improve both fidelity and controllability in these domains. Specifically, we propose: (1) a training-free holistic feature extraction pipeline inspired by noise correlation for point pattern synthesis, (2) (2) a decoupled representation and correlation embedding space for user-friendly point pattern editing, (3) a new perspective on integrating blue noise correlations into the training and sampling of diffusion models, and (4) a unified pipeline with noisy degraded data augmentation for fine-tuning diffusion models to enable simultaneous stereo video generation and restoration.
Our methods demonstrate the capability of outperforming existing state-of-the-art techniques and highlight the untapped potential of noise structure as a guiding principle in visual synthesis. These findings open new avenues for controllable and high-quality graphics content generation and editing.