RESUMEN
We present a new data-driven approach for extracting geometric and structural information from a single spherical panorama of an interior scene, and for using this information to render the scene from novel points of view, enhancing 3D immersion in VR applications. The approach copes with the inherent ambiguities of single-image geometry estimation and novel view synthesis by focusing on the very common case of Atlanta-world interiors, bounded by horizontal floors and ceilings and vertical walls. Based on this prior, we introduce a novel end-to-end deep learning approach to jointly estimate the depth and the underlying room structure of the scene. The prior guides the design of the network and of novel domain-specific loss functions, shifting the major computational load on a training phase that exploits available large-scale synthetic panoramic imagery. An extremely lightweight network uses geometric and structural information to infer novel panoramic views from translated positions at interactive rates, from which perspective views matching head rotations are produced and upsampled to the display size. As a result, our method automatically produces new poses around the original camera at interactive rates, within a working area suitable for producing depth cues for VR applications, especially when using head-mounted displays connected to graphics servers. The extracted floor plan and 3D wall structure can also be used to support room exploration. The experimental results demonstrate that our method provides low-latency performance and improves over current state-of-the-art solutions in prediction accuracy on available commonly used indoor panoramic benchmarks.
RESUMEN
Nowadays 360° cameras, capable to capture full environments in a single shot, are increasingly being used in a variety of Extended Reality (XR) applications that require specific Diminished Reality (DR) techniques to conceal selected classes of objects. In this work, we present a new data-driven approach that, from an input 360° image of a furnished indoor space automatically returns, with very low latency, an omnidirectional photorealistic view and architecturally plausible depth of the same scene emptied of all clutter. Contrary to recent data-driven inpainting methods that remove single user-defined objects based on their semantics, our approach is holistically applied to the entire scene, and is capable to separate the clutter from the architectural structure in a single step. By exploiting peculiar geometric features of the indoor environment, we shift the major computational load on the training phase and having an extremely lightweight network at prediction time. Our end-to-end approach starts by calculating an attention mask of the clutter in the image based on the geometric difference between full and empty scene. This mask is then propagated through gated convolutions that drive the generation of the output image and its depth. Returning the depth of the resulting structure allows us to exploit, during supervised training, geometric losses of different orders, including robust pixel-wise geometric losses and high-order 3D constraints typical of indoor structures. The experimental results demonstrate that our method provides interactive performance and outperforms current state-of-the-art solutions in prediction accuracy on available commonly used indoor panoramic benchmarks. In addition, our method presents consistent quality results even for scenes captured in the wild and for data for which there is no ground truth to support supervised training.
RESUMEN
We report on our work on the development of a novel holographic display technology, capable of targeting multiple freely moving naked eye viewers, and of a demonstrator, exploiting this technology to provide medical specialists with a truly interactive collaborative 3D environment for diagnostic discussions and/or pre-operative planning.
Asunto(s)
Simulación por Computador , Holografía , Interfaz Usuario-Computador , Terminales de Computador , Medicina , EspecializaciónRESUMEN
Mastoidectomy is one of the most common surgical procedures relating to the petrous bone. In this paper we describe our preliminary results in the realization of a virtual reality mastoidectomy simulator. Our system is designed to work on patient-specific volumetric object models directly derived from 3D CT and MRI images. The paper summarizes the detailed task analysis performed in order to define the system requirements, introduces the architecture of the prototype simulator, and discusses the initial feedback received from selected end users.
Asunto(s)
Simulación por Computador , Retroalimentación , Apófisis Mastoides/cirugía , Cirugía Asistida por Computador/instrumentación , Tacto , Interfaz Usuario-Computador , Sistemas de Computación , Humanos , Imagenología Tridimensional , Análisis y Desempeño de TareasRESUMEN
We describe a strategy for collecting experimental data and validating a bone-burr haptic contact model developed in a virtual surgical training system for middle ear surgery. The validation strategy is based on the analysis of data acquired during virtual and real burring sessions. Our approach involves intensive testing of the surgical simulator by expert surgeons and trainees as well as experimental data acquisition in a controlled environment.
Asunto(s)
Simulación por Computador , Oído Medio/cirugía , Modelos Educacionales , Hueso Temporal/cirugía , Humanos , Interfaz Usuario-ComputadorRESUMEN
Large scale and structurally complex volume datasets from high-resolution 3D imaging devices or computational simulations pose a number of technical challenges for interactive visual analysis. In this paper, we present the first integration of a multiscale volume representation based on tensor approximation within a GPU-accelerated out-of-core multiresolution rendering framework. Specific contributions include (a) a hierarchical brick-tensor decomposition approach for pre-processing large volume data, (b) a GPU accelerated tensor reconstruction implementation exploiting CUDA capabilities, and (c) an effective tensor-specific quantization strategy for reducing data transfer bandwidth and out-of-core memory footprint. Our multiscale representation allows for the extraction, analysis and display of structural features at variable spatial scales, while adaptive level-of-detail rendering methods make it possible to interactively explore large datasets within a constrained memory footprint. The quality and performance of our prototype system is evaluated on large structurally complex datasets, including gigabyte-sized micro-tomographic volumes.
Asunto(s)
Gráficos por Computador , Imagenología Tridimensional/estadística & datos numéricos , Algoritmos , Animales , Simulación por Computador , Bases de Datos Factuales , Hominidae/anatomía & histología , Lagartos/anatomía & histología , Modelos Anatómicos , Diente Molar/anatomía & histología , Microtomografía por Rayos X/estadística & datos numéricosRESUMEN
The currently observed exponentially increasing size of 3D models prohibits rendering them using brute force methods. Researchers have proposed various output-sensitive rendering algorithms to overcome this challenge. This article provides an overview of this technology.