Paul Guerrero is a Research Scientist at Adobe. Previously, he was a Post-Doc at UCL in Niloy Mitra’s group, a visiting PhD/PostDoc at KAUST, working with Peter Wonka, and a visiting Post-Doc at Stanford, working with Leonidas Guibas. Paul received his PhD at the Vienna University of Technology under the supervision of Michael Wimmer. His research focuses on shape analysis and on learning irregular structures, such as graphs, meshes, or vector graphics, combining methods from machine learning, optimization, and computational geometry. Paul has developed several structure-based methods to generate and edit 2D and 3D shapes. More information is available on his homepage.


TileGen: Tileable, Controllable Material Generation and Capture

Zhou, X., Hašan, M., Deschaintre, V., Guerrero, P., Sunkavalli, K., Kalantari, N. (Dec. 1, 2022)

Siggraph Asia Proc.

MatFormer: A Generative Model for Procedural Materials

Guerrero, P., Hašan, M., Sunkavalli, K., Měch, R., Boubekeur, T., Mitra, N. (Aug. 8, 2022)

ACM Transactions on Graphics (Proc. SIGGRAPH 2022)

Node Graph Optimization Using Differentiable Proxies

Hu, Y., Guerrero, P., Hašan, M., Rushmeier, H., Deschaintre, V. (Aug. 1, 2022)

Siggraph proc.

Controlling Material Appearance by Examples

Hu, Y., Hašan, M., Guerrero, P., Rushmeier, H., Deschaintre, V. (Jul. 1, 2022)

Computer Graphics Forum (EGSR Proceedings)

Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images

Lei, J., Sridhar, S., Guerrero, P., Sung, M., Mitra, N., Guibas, L. (Aug. 24, 2020)

European Conference on Computer Vision (ECCV)