Search Results

Now showing 1 - 10 of 13
  • Item
    MTV-Player: Interactive Spatio-Temporal Exploration of Compressed Large-Scale Time-Varying Rectilinar Scalar Volumes
    (The Eurographics Association, 2019) Díaz, Jose; Marton, Fabio; Gobbetti, Enrico; Agus, Marco and Corsini, Massimiliano and Pintus, Ruggero
    We present an approach for supporting fully interactive exploration of massive time-varying rectilinear scalar volumes on commodity platforms. We decompose each frame into a forest of bricked octrees. Each brick is further subdivided into smaller blocks, which are compactly approximated by quantized variable-length sparse linear combinations of prototype blocks stored in a data-dependent dictionary learned from the input sequence. This variable bit-rate compact representation, obtained through a tolerance-driven learning and approximation process, is stored in a GPU-friendly format that supports direct adaptive streaming to the GPU with spatial and temporal random access. An adaptive compression-domain renderer closely coordinates off-line data selection, streaming, decompression, and rendering. The resulting system provides total control over the spatial and temporal dimensions of the data, supporting the same exploration metaphor as traditional video players. Since we employ a highly compressed representation, the bandwidth provided by current commodity platforms proves sufficient to fully stream and render dynamic representations without relying on partial updates, thus avoiding any unwanted dynamic effects introduced by current incremental loading approaches. Moreover, our variable-rate encoding based on sparse representations provides high-quality approximations, while offering real-time decoding and rendering performance. The quality and performance of our approach is demonstrated on massive time-varying datasets at the terascale, which are nonlinearly explored at interactive rates on a commodity graphics PC.
  • Item
    Two Examples of GPGPU Acceleration of Memory-intensive Algorithms
    (The Eurographics Association, 2010) Marras, Stefano; Mura, Claudio; Gobbetti, Enrico; Scateni, Riccardo; Scopigno, Roberto; Enrico Puppo and Andrea Brogni and Leila De Floriani
    The advent of GPGPU technologies has allowed for sensible speed-ups in many high-dimension, memory-intensive computational problems. In this paper we demonstrate the e ectiveness of such techniques by describing two applications of GPGPU computing to two di erent subfields of computer graphics, namely computer vision and mesh processing. In the first case, CUDA technology is employed to accelerate the computation of approximation of motion between two images, known also as optical flow. As for mesh processing, we exploit the massivelyparallel architecture of CUDA devices to accelerate the face clustering procedure that is employed in many recent mesh segmentation algorithms. In both cases, the results obtained so far are presented and thoroughly discussed, along with the expected future development of the work.
  • Item
    SPIDER: SPherical Indoor DEpth Renderer
    (The Eurographics Association, 2022) Tukur, Muhammad; Pintore, Giovanni; Gobbetti, Enrico; Schneider, Jens; Agus, Marco; Cabiddu, Daniela; Schneider, Teseo; Allegra, Dario; Catalano, Chiara Eva; Cherchi, Gianmarco; Scateni, Riccardo
    Today's Extended Reality (XR) applications that call for specific Diminished Reality (DR) strategies to hide specific classes of objects are increasingly using 360? cameras, which can capture entire areas in a single picture. In this work, we present an interactive-based image editing and rendering system named SPIDER, that takes a spherical 360? indoor scene as input. The system incorporates the output of deep learning models to abstract the segmentation and depth images of full and empty rooms to allow users to perform interactive exploration and basic editing operations on the reconstructed indoor scene, namely: i) rendering of the scene in various modalities (point cloud, polygonal, wireframe) ii) refurnishing (transferring portions of rooms) iii) deferred shading through the usage of precomputed normal maps. These kinds of scene editing and manipulations can be used for assessing the inference from deep learning models and enable several Mixed Reality (XR) applications in areas such as furniture retails, interior designs, and real estates. Moreover, it can also be useful in data augmentation, arts, designs, and paintings.
  • Item
    Towards Advanced Volumetric Display of the Human Musculoskeletal System
    (The Eurographics Association, 2008) Agus, Marco; Giachetti, Andrea; Gobbetti, Enrico; Guitián, José Antonio Iglesias; Marton, Fabio; Vittorio Scarano and Rosario De Chiara and Ugo Erra
    We report on our research results on effective volume visualization techniques for medical and anatomical data. Our volume rendering approach employs GPU accelerated out-of-core direct rendering algorithms to fully support high resolution, 16 bits, raw medical datasets as well as segmentation. Images can be presented on a special light field display based on projection technology. Human anatomical data appear to moving viewers floating in the light field display space and can be interactively manipulated.
  • Item
    Edge Adaptive and Energy Preserving Volume Upscaling for High Quality Volume Rendering
    (The Eurographics Association, 2010) Giachetti, Andrea; Guitián, J. A. Iglesias; Gobbetti, Enrico; Enrico Puppo and Andrea Brogni and Leila De Floriani
    We describe an edge-directed optimization-based method for volumetric data supersampling. The method is based on voxel splitting and iterative refinement performed with a greedy optimization driven by the smoothing of second order gray level derivatives and the assumption that the average gray level in the original voxels region cannot change. Due to these assumptions, the method, which is the 3D extension of a recently proposed technique, is particularly suitable for upscaling medical imaging data creating physically reasonable voxel values and overcoming the so-called partial volume effect. The good quality of the results obtained is demonstrated through experimental tests. Furthermore, we show how offline 3D upscaling of volumes can be coupled with recent techniques to perform high quality volume rendering of large datasets, obtaining a better inspection of medical volumetric data
  • Item
    Evaluating AI-based static stereoscopic rendering of indoor panoramic scenes
    (The Eurographics Association, 2024) Jashari, Sara; Tukur, Muhammad; Boraey, Yehia; Alzubaidi, Mahmood; Pintore, Giovanni; Gobbetti, Enrico; Villanueva, Alberto Jaspe; Schneider, Jens; Fetais, Noora; Agus, Marco; Caputo, Ariel; Garro, Valeria; Giachetti, Andrea; Castellani, Umberto; Dulecha, Tinsae Gebrechristos
    Panoramic imaging has recently become an extensively used technology for the representation and exploration of indoor environments. Panoramic cameras generate omnidirectional images that provide a comprehensive 360-degree view, making them a valuable tool for applications such as virtual tours in real estate, architecture, and cultural heritage. However, constructing truly immersive experiences from panoramic images presents challenges, particularly in generating panoramic stereo pairs that offer consistent depth cues and visual comfort across all viewing directions. Traditional stereo-imaging techniques do not directly apply to spherical panoramic images, requiring complex processing to avoid artifacts that can disrupt immersion. To address these challenges, various imaging and processing technologies have been developed, including multi-camera systems and computational methods that generate stereo images from a single panoramic input. Although effective, these solutions often involve complicated hardware and processing pipelines. Recently, deep learning approaches have emerged, enabling novel view generation from single panoramic images. While these methods show promise, they have not yet been thoroughly evaluated in practical scenarios. This paper presents a series of evaluation experiments aimed at assessing different technologies for creating static stereoscopic environments from omnidirectional imagery, with a focus on 3DOF immersive exploration. A user study was conducted using a WebXR prototype and a Meta Quest 3 headset to quantitatively and qualitatively compare traditional image composition techniques with AI-based methods. Our results indicate that while traditional methods provide a satisfactory level of immersion, AI-based generation is nearing a quality level suitable for deployment in web-based environments.
  • Item
    Practical Free-form RTI Acquisition with Local Spot Lights
    (The Eurographics Association, 2016) Pintus, Ruggero; Ciortan, Irina Mihaela; Giachetti, Andrea; Gobbetti, Enrico; Giovanni Pintore and Filippo Stanco
    We present an automated light calibration pipeline for free-form acquisition of shape and reflectance of objects using common off-the-shelf illuminators, such as LED lights, that can be placed arbitrarily close to the objects. We acquire multiple digital photographs of the studied object shot from a stationary camera. In each photograph, a light is freely positioned around the object in order to cover a wide variety of illumination directions. While common free-form acquisition approaches are based on the simplifying assumptions that the light sources are either sufficiently far from the object that all incoming light can be modeled using parallel rays, or that lights are local points emitting uniformly in space, we use the more realistic model of a scene lit by a moving local spot light with exponential fall-off depending on the cosine of the angle between the spot light optical axis and the illumination direction, raised to the power of the spot exponent. We recover all spot light parameters using a multipass numerical method. First, light positions are determined using standard methods used in photometric stereo approaches. Then, we exploit measures taken on a Lambertian reference planar object to recover the spot light exponent and the per-image spot light optical axis; we minimize the difference between the observed reflectance and the reflectance synthesized by using the near-field Lambertian equation. The optimization is performed in two passes, first generating a starting solution and then refining it using a Levenberg-Marquardt iterative minimizer. We demonstrate the effectiveness of the method based on an error analysis performed on analytical datasets, as well as on real-world experiments.
  • Item
    Guiding Lens-based Exploration using Annotation Graphs
    (The Eurographics Association, 2021) Ahsan, Moonisa; Marton, Fabio; Pintus, Ruggero; Gobbetti, Enrico; Frosini, Patrizio and Giorgi, Daniela and Melzi, Simone and Rodolà, Emanuele
    We introduce a novel approach for guiding users in the exploration of annotated 2D models using interactive visualization lenses. Information on the interesting areas of the model is encoded in an annotation graph generated at authoring time. Each graph node contains an annotation, in the form of a visual markup of the area of interest, as well as the optimal lens parameters that should be used to explore the annotated area and a scalar representing the annotation importance. Graph edges are used, instead, to represent preferred ordering relations in the presentation of annotations. A scalar associated to each edge determines the strength of this prescription. At run-time, the graph is exploited to assist users in their navigation by determining the next best annotation in the database and moving the lens towards it when the user releases interactive control. The selection is based on the current view and lens parameters, the graph content and structure, and the navigation history. This approach supports the seamless blending of an automatic tour of the data with interactive lens-based exploration. The approach is tested and discussed in the context of the exploration of multi-layer relightable models.
  • Item
    DDD: Deep indoor panoramic Depth estimation with Density maps consistency
    (The Eurographics Association, 2024) Pintore, Giovanni; Agus, Marco; Signoroni, Alberto; Gobbetti, Enrico; Caputo, Ariel; Garro, Valeria; Giachetti, Andrea; Castellani, Umberto; Dulecha, Tinsae Gebrechristos
    We introduce a novel deep neural network for rapid and structurally consistent monocular 360◦ depth estimation in indoor environments. The network infers a depth map from a single gravity-aligned or gravity-rectified equirectangular image of the environment, ensuring that the predicted depth aligns with the typical depth distribution and features of cluttered interior spaces, which are usually enclosed by walls, ceilings, and floors. By leveraging the distinct characteristics of vertical and horizontal features in man-made indoor environments, we introduce a lean network architecture that employs gravity-aligned feature flattening and specialized vision transformers that utilize the input's omnidirectional nature, without segmentation into patches and positional encoding. To enhance the structural consistency of the predicted depth, we introduce a new loss function that evaluates the consistency of density maps by projecting points derived from the inferred depth map onto horizontal and vertical planes. This lightweight architecture has very small computational demands, provides greater structural consistency than competing methods, and does not require the explicit imposition of strong structural priors.
  • Item
    Visual Enhancements for Improved Interactive Rendering on Light Field Displays
    (The Eurographics Association, 2011) Agus, Marco; Pintore, Giovanni; Marton, Fabio; Gobbetti, Enrico; Zorcolo, Antonio; Andrea F. Abate and Michele Nappi and Genny Tortora
    Rendering of complex scenes on a projector-based light field display requires 3D content adaptation in order to provide comfortable viewing experiences in all conditions. In this paper we report about our approach to improve visual experiences while coping with the limitations in the effective field of depth and the angular field of view of the light field display. We present adaptation methods employing non-linear depth mapping and depth of field simulation which leave large parts of the scene unmodified, while modifying the other parts in a non-intrusive way. The methods are integrated in an interactive visualization system for the inspection of massive models on a large scale 35MPixel light field display. Preliminary results of subjective evaluation demonstrate that our rendering adaptation techniques improve visual comfort without affecting the overall depth perception.