Deep Scene Synthesis of Atlanta-World Interiors from a Single Omnidirectional Image.

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.

Instant Automatic Emptying of Panoramic Indoor Scenes.

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.

Interactive multiscale tensor reconstruction for multiresolution volume visualization.

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.

Massive-model rendering techniques.

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.

A holographic collaborative medical visualization system.

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.

Mastoidectomy simulation with combined visual and haptic feedback.

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.

A haptic model of a bone-cutting burr.

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.