Surface reconstruction techniques for imperfect raw-data

Summary form only given. In my talk I will present some surface reconstruction techniques that handle imperfect data. Such data is common in raw scans and contains large missing parts, ghost outliers and under-sampled regions. We explore reconstruction techniques that focus on such problematic regions. Our general goal is recovering the expected shape in terms of global topology and local geometric detail. I will present different methods that focus on several essential problems of imperfect data reconstruction: In the first part I will present a deformable model method that recovers a watertight surface and well interprets the topology of imperfect scans. Then, I will briefly introduce an interactive topology-aware reconstruction method that uses minimal user input to correctly reconstruct regions where the topology of the model cannot be automatically induced. I will also show how the reconstruction can be improved with the use of local priors and a visibility prior. Then, I will present a registration technique that handle noisy data. The technique allows registering raw noisy data, possibly contaminated with outliers, without pre-filtering or denoising the data. Finally, if time permits, I will present a novel approach based on the argument that man-made models can be distilled using a few special 1D wires and their mutual relations. Maintaining the properties of such a small number of wires allows preserving the defining characteristics of the entire object. The new method takes an analyze-and-edit approach, where prior to editing, it performs a light-weight analysis of the input shape to extract a descriptive set of wires. Analyzing the individual and mutual properties of the wires, and augmenting them with geometric attributes makes them intelligent and ready to be manipulated. Editing the object by modifying the intelligent wires leads to a powerful editing framework that retains the original design intent and object characteristics.