A5001550110- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- Advanced Optical Sensing Technologies
- Visual Attention and Saliency Detection
- Image Enhancement Techniques
- 3D Shape Modeling and Analysis
- Visual perception and processing mechanisms
- Color Science and Applications
- Random lasers and scattering media
- Image and Video Quality Assessment
- Virtual Reality Applications and Impacts
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
- 3D Surveying and Cultural Heritage
- Advanced Fluorescence Microscopy Techniques
- Advanced Optical Imaging Technologies
- Aesthetic Perception and Analysis
- Optical Coherence Tomography Applications
- Optical Imaging and Spectroscopy Techniques
- Remote Sensing and LiDAR Applications
- Magnetic confinement fusion research
- Optical measurement and interference techniques
- Image Processing Techniques and Applications
- Particle accelerators and beam dynamics
- Data Visualization and Analytics
Universidad de Zaragoza
2016-2025
Universidad de Ingeniería y Tecnología
2024
Hydronalix (United States)
2024
University of Puerto Rico-Mayaguez
2023-2024
University of Puerto Rico System
2024
Federico Santa María Technical University
2023
Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di Legnaro
2021-2023
Laboratoire d’Imagerie Biomédicale
2023
Inter-American Development Bank
2023
Universitas Islam Al-Azhar Mataram
2021-2022
Understanding how people explore immersive virtual environments is crucial for many applications, such as designing reality (VR) content, developing new compression algorithms, or learning computational models of saliency visual attention. Whereas a body recent work has focused on modeling in desktop viewing conditions, VR very different from these conditions that behavior governed by stereoscopic vision and the complex interaction head orientation, gaze, other kinematic constraints. To...
The numerous works on media retargeting call for a methodological approach evaluating results. We present the first comprehensive perceptual study and analysis of image retargeting. First, we create benchmark images conduct large scale user to compare representative number state-of-the-art methods. Second, users' responses, where find that humans in general agree evaluation results show some methods are consistently more favorable than others. Third, examine whether computational distance...
The numerous works on media retargeting call for a methodological approach evaluating results. We present the first comprehensive perceptual study and analysis of image retargeting. First, we create benchmark images conduct large scale user to compare representative number state-of-the-art methods. Second, users' responses, where find that humans in general agree evaluation results show some methods are consistently more favorable than others. Third, examine whether computational distance...
We present a novel hyperspectral image reconstruction algorithm, which overcomes the long-standing tradeoff between spectral accuracy and spatial resolution in existing compressive imaging approaches. Our method consists of two steps: First, we learn nonlinear representations from real-world datasets; for this, build convolutional autoencoder allows reconstructing its own input through encoder decoder networks. Second, introduce optimization method, jointly regularizes fidelity learned...
We present femto-photography , a novel imaging technique to capture and visualize the propagation of light. With an effective exposure time 1.85 picoseconds (ps) per frame, we reconstruct movies ultrafast events at equivalent resolution about one half trillion frames second. Because cameras with this shutter speed do not exist, re-purpose modern hardware record ensemble average repeatable that are synchronized streak sensor, in which arrival light from scene is coded sensor's spatial...
The ITER Neutral Beam Test Facility (NBTF), called PRIMA (Padova Research on Megavolt Accelerator), is hosted in Padova, Italy and includes two experiments: MITICA, the full-scale prototype of heating neutral beam injector, SPIDER, full-size radio frequency negative-ions source. NBTF realization exploitation SPIDER MITICA have been recognized as necessary to make future operation injectors efficient reliable, fundamental achievement thermonuclear-relevant plasma parameters ITER. This paper...
Abstract Decomposing an input image into its intrinsic shading and reflectance components is a long‐standing ill‐posed problem. We present novel algorithm that requires no user strokes works on single image. Based simple assumptions about luminance, we first find clusters of similar in the image, build linear system describing connections relations between them. Our are less restrictive than widely‐adopted Retinex‐based approaches, can be further relaxed conflicting situations. The resulting...
The numerous works on media retargeting call for a methodological approach evaluating results. We present the first comprehensive perceptual study and analysis of image retargeting. First, we create benchmark images conduct large scale user to compare representative number state-of-the-art methods. Second, users' responses, where find that humans in general agree evaluation results show some methods are consistently more favorable than others. Third, examine whether computational distance...
Capturing spatially-varying bidirectional reflectance distribution functions (SVBRDFs) of 3D objects with just a single, hand-held camera (such as an off-the-shelf smartphone or DSLR camera) is difficult, open problem. Previous works are either limited to planar geometry, rely on previously scanned thus limiting their practicality. There several technical challenges that need be overcome: First, the built-in flash almost colocated lens, and at fixed position; this severely hampers sampling...
Recent advances in ultra-fast imaging have triggered many promising applications graphics and vision, such as capturing transparent objects, estimating hidden geometry materials, or visualizing light motion. There is, however, very little work regarding the effective simulation analysis of transient transport, where speed can no longer be considered infinite. We first introduce path integral framework, formally describing transport state. then analyze difficulties arising when considering...
Time-of-flight (ToF) imaging has become a widespread technique for depth estimation, allowing affordable off-the-shelf cameras to provide maps in real time. However, multipath interference (MPI) resulting from indirect illumination significantly degrades the captured depth. Most previous works have tried solve this problem by means of complex hardware modifications or costly computations. In work, we avoid these approaches and propose new correct errors caused MPI, which requires no camera...
The ITER project requires additional heating by two neutral beam injectors, each accelerating to 1 MV a 40 A of negative deuterium ions, deliver the plasma power about 17 MW for one hour. As these requirements have never been experimentally met, it was recognized as necessary setup test facility, PRIMA (Padova Research on Megavolt Accelerator), in Italy, including full-size ion source, SPIDER, and prototype whole injector, MITICA, aiming develop injectors be installed ITER. This realization...
Recent works have demonstrated non-line of sight (NLOS) reconstruction by using the time-resolved signal from multiply scattered light. These combine ultrafast imaging systems with computation, which back-projects recorded space-time to build a probabilistic map hidden geometry. Unfortunately, this computation is slow, becoming bottleneck as technology improves. In work, we propose new back-projection technique for NLOS reconstruction, up thousand times faster than previous almost no quality...
Virtual characters contribute strongly to the entire visuals of 3D animated films. However, designing believable remains a challenging task. Artists rely on stylization increase appeal or expressivity, exaggerating softening specific features. In this paper we analyze two most influential factors that define how character looks: shape and material. With help artists, design set carefully crafted stimuli consisting different levels for both parameters, combinations affect perceived realism,...
Abstract Current HDR acquisition techniques are based on either (i) fusing multibracketed, low dynamic range (LDR) images, (ii) modifying existing hardware and capturing different exposures simultaneously with multiple sensors, or (iii) reconstructing a single image spatially‐varying pixel exposures. In this paper, we propose novel algorithm to recover high‐quality HDRI images from single, coded exposure. The proposed reconstruction method builds recently‐introduced ideas of convolutional...
We present a method to decompose video into its intrinsic components of reflectance and shading, plus number related example applications in editing such as segmentation, stylization, material editing, recolorization color transfer. Intrinsic decomposition is an ill-posed problem, which becomes even more challenging the case due need for temporal coherence potentially large memory requirements global approach. Additionally, user interaction should be kept minimum order ensure efficiency....
Most existing image content has low dynamic range (LDR), which necessitates effective methods to display such legacy on high (HDR) devices. Reverse tone mapping operators (rTMOs) aim take LDR as input and adjust the contrast intelligently yield output that recreates HDR experience. In this paper we show current rTMO approaches fall short when is not exposed properly. More specifically, report a series of perceptual experiments using Brightside that, while rTMOs perform well for under-exposed...
This paper presents a method for measuring the similarity in style between two pieces of vector art, independent content. Similarity is measured by differences four types features: color, shading, texture, and stroke. Feature weightings are learned from crowdsourced experiments. perceptual enables style-based search. Using our search feature, we demonstrate an application that allows users to create stylistically-coherent clip art mash-ups.
Transient imaging has recently made a huge impact in the computer graphics and vision fields. By capturing, reconstructing, or simulating light transport at extreme temporal resolutions, researchers have proposed novel techniques to show movies of motion, see around corners, detect objects highly-scattering media, infer material properties from distance, name few. The key idea is leverage wealth information domain pico nanosecond resolution, usually lost during capture-time integration. This...
We present a novel, compact single-shot hyperspectral imaging method. It enables capturing images using conventional DSLR camera equipped with just an ordinary refractive prism in front of the lens. Our computational method reconstructs full spectral information scene from dispersion over edges. setup requires no coded aperture mask, slit, and collimating optics, which are necessary for traditional systems. is thus very cost-effective, while still highly accurate. tackle two main problems:...
We present a method for adding parallax and real-time playback of 360° videos in Virtual Reality headsets. In current video players, the does not respond to translational head movement, which reduces feeling immersion, causes motion sickness some viewers. Given its corresponding depth (provided by stereo stitching algorithms), naive image-based rendering approach would use generate 3D mesh around viewer, then translate it appropriately as viewer moves their head. However, this breaks at...