Now showing items 1-3 of 3
3D Reconstruction and Rendering from High Resolution Light Fields
(ETH Zurich, 2015)
This thesis presents a complete processing pipeline of densely sampled, high resolution light fields, from acquisition to rendering. The key components of the pipeline include 3D scene reconstruction, geometry-driven ...
The Smart Point Cloud: Structuring 3D intelligent point data
Discrete spatial datasets known as point clouds often lay the groundwork for decision-making applications. E.g., we can use such data as a reference for autonomous cars and robot’s navigation, as a layer for floor-plan’s ...
Self-Supervised Shape and Appearance Modeling via Neural Differentiable Graphics
Inferring 3D shape and appearance from natural images is a fundamental challenge in computer vision. Despite recent progress using deep learning methods, a key limitation is the availability of annotated training data, as ...