Over the past decade, 3D graphics have become highly detailed to mimic the real world, exploding their size and complexity. Certain applications and device constraints necessitate their simplification and/or lossy compression, which can degrade their visual quality. Thus, to ensure the best Quality of Experience (QoE), it is important to evaluate the visual quality to accurately drive the compression and find the right compromise between visual quality and data size. In this work, we focus on subjective and objective quality assessment of textured 3D meshes. We first establish a large-scale dataset, which includes 55 source models quantitatively characterized in terms of geometric, color, and semantic complexity, and corrupted by combinations of 5 types of compression-based distortions applied on the geometry, texture mapping and texture image of the meshes. This dataset contains over 343k distorted stimuli. We propose an approach to select a challenging subset of 3000 stimuli for which we collected 148929 quality judgments from over 4500 participants in a large-scale crowdsourced subjective experiment. Leveraging our subject-rated dataset, a learning-based quality metric for 3D graphics was proposed. Our metric demonstrates state-of-the-art results on our dataset of textured meshes and on a dataset of distorted meshes with vertex colors. Finally, we present an application of our metric and dataset to explore the influence of distortion interactions and content characteristics on the perceived quality of compressed textured meshes.
Abstract. Digital 3D representations of urban areas, through their growing availability, are a helpful tool to better understand a territory. However, they lack contextual information about, for example, the history or functionality of buildings. On another side, multimedia documents like images, videos or texts usually contain such information. Crossing these two types of data can therefore help in the analysis and understanding of the organization of our cities. This could also be used to develop document search based on spatial navigation, instead of the classical textual query. In this paper, we propose four approaches to integrate multimedia documents in a 3D urban scene, allowing to contextualize the scene with any type of media. We combine these integration approaches with user guidance modes that allows to guide the user through the consumption of these media and support its understanding of the territory. We demonstrate the usefulness of these techniques in the context of different projects within the Lyon area (France). The use of multimedia documents integrated into a digital tour allows, for example, the iconic buildings to be contextualised or to understand the evolution of a territory through time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.