We propose a new learning-based algorithm which is able to predict high quality viewpoints directly on 3D models. The key to learning viewpoints is a novel approach to resolve label ambiguities, in the form of dynamic label generation, which adapts the network target during training, and enables our network to learn viewpoints for various viewpoint quality measures. By learning solely on unstructured 3D point information, our approach is robust under mesh quality changes, and the viewpoint prediction is separated from the rendering process during evaluation.

Key wordsEstimates of the spectrum of matrices, operator matrices of unbounded operators MSC (2010) 47A10, 15A42We present a Gershgorin's type result on the localisation of the spectrum of a matrix. Our method is elementary as it relies upon the method of Schur complements, but it outperforms the one based on the Cassini ovals of Ostrovski and Brauer. Furthermore, it yields estimates that hold without major differences in the cases of both scalar and operator matrices. Several refinements of known results are obtained.

View quality measures compute scores for given views and are used to determine an optimal view in viewpoint selection tasks. Unfortunately, despite the wide adoption of these measures, they are rather based on computational quantities, such as entropy, than human preferences. To instead tailor viewpoint measures towards humans, view quality measures need to be able to capture human viewpoint preferences. Therefore, we introduce a large-scale crowdsourced data set, which contains 58k annotated viewpoints for 3220 ModelNet40 models. Based on this data, we derive a neural view quality measure abiding to human preferences. We further demonstrate that this view quality measure not only generalizes to models unseen during training, but also to unseen model categories. We are thus able to predict view qualities for single images, and directly predict human preferred viewpoints for 3D models by exploiting point-based learning technology, without requiring to generate intermediate images or sampling the view sphere. We will detail our data collection procedure, describe the data analysis and model training and will evaluate the predictive quality of our trained viewpoint measure on unseen models and categories. To our knowledge, this is the first deep learning approach to predict a view quality measure solely based on human preferences.

No abstract

No abstract