PhD Thesis - Neural Surfaces
This thesis discusses map-based neural representations as effective alternative to meshes in geometry processing tasks.
[PDF]
I obtained my PhD from University College London, supervised by Niloy J. Mitra and Noam Aigerman. My studies were sponsored by FAI CDT. My research lies at the intersection of computer vision, computer graphics and machine learning. Prior to that, I obtained my MSc and BSc at Politecnico di Milano.
This thesis discusses map-based neural representations as effective alternative to meshes in geometry processing tasks.
[PDF]
Through pre-trained ViT(DinoV2) we extract (visual) semantic correspondences to optimize inter-surface mapping.
[PDF]
[Webpage]
[Code]
[Video]
Neural surface representation disentangling coarse geometry from fine details. Thanks to CNNs inductive bias, the description is compact and allows editing....
[PDF]
[Webpage]
[Code]
Neural representation of surface maps, allowing optimization of differentiable quantities in inter-surface maps.
[PDF]
[Webpage]
[Code]
Fast scene point cloud simplification leveraging semantic information.
[PDF]
[Webpage]
Next Best View prediction based on photogrammetry principles."
[PDF]
[Webpage]
[Code]
Novel player represenation in Physically-Interactive RoboGames.
[PDF]
[Webpage]
[Code]