Learning Human Viewpoint Preferences from Sparsely Annotated Models

Abstract

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.

Fast Best Viewpoint Selection with Geometry-Enhanced Multiple Views and Cross-Modal Distillation

“…Deep-learning approaches [21] select the optimal viewpoint by conducting multi-view renderings through a predefined sequence of viewpoints, then identifying the optimal viewpoint according to a learned sequence of view scores. Although these approaches effectively capture human selection preferences, they face two primary challenges in practical applications: first, they require extensive pre-rendering of views, which consumes significant resources and might overlook the optimal viewpoints; second, obtaining large-scale human-annotated data is costly and labor-intensive.…”

Viewpoint Selection for 3D-Games with f-Divergences

“…Hartwig et al [ 36 ] introduced a neural view quality measure aligned with human preferences. The study demonstrated that this measure generalized not only to models unseen during training but also to unseen model categories.…”

: A Cluster Ambiguity Measure for Estimating Perceptual Variability in Visual Clustering

“…A reliable method to evaluate the ambiguity of a scatterplot is directly measuring perceptual variability via human experiments [26]. However, this process is costly and not scalable.…”