William Smith

William Smith is a Professor in the Department of Computer Science at the University of York, where he leads the Vision, Graphics and Learning (VGL) research group. He holds a BSc and PhD in Computer Science from the University of York, completed in 2002 and 2007 respectively. He has served in key roles including Director of Admissions, PGT AI Programme Lead, and Research Group Lead. He is an Associate Editor for the journal Pattern Recognition and was a Royal Academy of Engineering/The Leverhulme Trust Senior Research Fellow from 2019 to 2020.

Education:

• BSc in Computer Science, University of York, 2002
• PhD in Computer Vision, University of York, 2007

His research lies at the intersection of computer vision, computer graphics, and machine learning. He focuses on physics-based and 3D vision, shape and appearance modeling, and the application of statistical and machine learning methods. Key application areas include face and body analysis, surveying and mapping, object capture, and inverse rendering. His work leverages advanced mathematical tools such as convex and nonlinear optimization, manifold learning, computational geometry, and low-level vision techniques.

His recent publications, spanning top venues like ECCV, NeurIPS, WACV, and IEEE T-PAMI, reflect a strong trend in neural scene representation, inverse rendering, and illumination modeling. Themes include relighting outdoor scenes, self-supervised pose estimation, spherical neural fields, and orientation-aware deep learning for omnidirectional inputs. These works demonstrate a consistent focus on integrating physical models with deep learning for robust and interpretable vision systems.

Scientific Awards:

• Royal Academy of Engineering/The Leverhulme Trust Senior Research Fellow (2019–2020)

William Smith supervises a team of nine PhD students and has advised several alumni who have gone on to research and industry roles. He has served in significant service roles including Area Chair for ICCV, CVPR, and 3DV, Programme Chair for BMVC 2020, General Chair for CVMP 2019, and reviewer for major conferences since 2008. He is actively involved in the academic community and continues to contribute to cutting-edge research through his leadership in the VGL group at York.

The Vision, Graphics and Learning (VGL) group, which he leads, conducts research in computer vision, graphics, and machine learning, with projects such as Branching Out (historic tree mapping), Senior Research Fellowship (model-based vision meets deep learning), Google Daydream (VR/AR head modeling), and LEAPP (polar archival photography). The group fosters a collaborative environment with both current and former members contributing to impactful research.