A5036884686- Image and Video Quality Assessment
- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- Virtual Reality Applications and Impacts
- 3D Shape Modeling and Analysis
- 3D Surveying and Cultural Heritage
- Video Coding and Compression Technologies
- Augmented Reality Applications
- Visual Attention and Saliency Detection
- Advanced Optical Imaging Technologies
- Remote Sensing and LiDAR Applications
- Multimedia Communication and Technology
- Color Science and Applications
- Video Surveillance and Tracking Methods
- Advanced Data Compression Techniques
- Image Enhancement Techniques
- Visual perception and processing mechanisms
- Industrial Vision Systems and Defect Detection
- Innovative Human-Technology Interaction
- Telecommunications and Broadcasting Technologies
- Evacuation and Crowd Dynamics
- Robotics and Automated Systems
- Video Analysis and Summarization
- Taxation and Legal Issues
- Anomaly Detection Techniques and Applications
Centrum Wiskunde & Informatica
2019-2025
University of Trieste
2021
École Polytechnique Fédérale de Lausanne
2016-2019
m. borges, 2 tiago a. fonseca, 3 ricardo l. de queiroz 4 and touradj ebrahimi 1Recent trends in multimedia technologies indicate the need for richer imaging modalities to increase user engagement with content.Among other alternatives, point clouds denote a viable solution that offers an immersive content representation, as witnessed by current activities JPEG MPEG standardization committees.As result of such efforts, is at final stages drafting emerging standard cloud compression, which we...
In recent years, point clouds have gained popularity as a promising representation for volumetric contents in immersive scenarios. Standardization bodies such MPEG been developing new compression standards cloud to reduce the volume of data, while maintaining an acceptable level visual quality. To do so, reliable metrics are needed order automatically estimate perceptual quality degraded contents. Whereas several objective developed assess geometrical impairment contents, fewer publications...
Point cloud representation has seen a surge of popularity in recent years, thanks to its capability reproduce volumetric scenes immersive scenarios. New compression solutions for streaming point contents have been proposed, which require objective quality metrics reliably assess the level degradation introduced by coding and transmission distortions. In this context, reduced reference aim predict visual transmitted contents, while requiring only small set features be sent addition streamed...
The recent advances in light field imaging, supported among others by the introduction of commercially available cameras, e.g., Lytro or Raytrix, are changing ways which visual content is captured and processed. Efficient storage delivery systems for images must rely on compression algorithms. Several methods to compress have been proposed recently. However, in-depth evaluations algorithms rarely reported. This paper aims at evaluation perceived quality comparing performance a few...
In the last years, light field imaging has experienced a surge of popularity among scientific community for its capability rendering 3D world in more immersive way. particular, several compression algorithms have been proposed to efficiently reduce amount data generated acquisition process, and different methodologies designed reliably evaluate visual quality compressed contents. this paper we propose dataset assessment images (VALID). The contains five contents at various bitrates, using...
In recent years, light field imaging has attracted the attention of academic and industrial communities thanks to its enhanced rendering capabilities that allow visualise contents in a more immersive interactive way. However, those come at cost considerable increase content size when compared traditional image video applications. Thus, advanced compression schemes are needed efficiently reduce volume data for storage delivery content. this paper, we introduce novel method images. The...
In recent years, the development of devices for acquisition and rendering 3D contents have facilitated diffusion immersive virtual reality experiences. particular, point cloud representation has emerged as a popular format volumetric photorealistic reconstructions dynamic real world objects, due to its simplicity versatility. To optimize delivery large amount data needed provide these experiences, adaptive streaming over HTTP is promising solution. order ensure best quality experience within...
Recently an impressive development in immersive technologies, such as Augmented Reality (AR), Virtual (VR) and 360<inline-formula><tex-math notation="LaTeX">${^\circ }$</tex-math></inline-formula> video, has been witnessed. However, methods for quality assessment have not keeping up. This paper studies of video from the cross-lab tests (involving ten laboratories more than 300 participants) carried out by Immersive Media Group (IMG) Video Quality Experts (VQEG). These were addressed to...
Virtual reality telecommunication systems promise to overcome the limitations of current real-time teleconferencing solutions by enabling a better sense immersion and fostering more natural interpersonal interactions. Many that currently enable immersive employ synthetic avatars represent their users. However, photorealistic reconstructions have been shown increase presence with respect in teleimmersive scenarios. In this article, we present VR2Gather, costumizable, end-to-end system...
This paper presents a Task-Free eye-tracking dataset for Dynamic Point Clouds (TF-DPC) aimed at investigating visual attention. The is composed of eye gaze and head movements collected from 24 participants observing 19 scanned dynamic point clouds in Virtual Reality (VR) environment with 6 degrees freedom. We compare the saliency maps generated this those prior task-dependent experiment (focused on quality assessment) to explore how high-level tasks influence human To measure similarity...
This paper reports results of subjective and objective quality assessments responses to a grand challenge on light field image compression. The goal the was collect evaluate new compression algorithms for images. In total seven proposals were received, out which five accepted further evaluations. For evaluations, conventional metrics used, whereas double stimulus continuous scale method selected perform assessments. Results show competitive performance among submitted proposals. However, in...
Virtual Reality (VR) and Augmented (AR) applications have seen a drastic increase in commercial popularity. Different representations been used to create 3D reconstructions for AR VR. Point clouds are one such representation characterized by their simplicity versatility, making them suitable real time applications, as reconstructing humans social virtual reality. In this study, we evaluate how the visual quality of digital humans, represented using point clouds, is affected compression...
This work presents an explorative behavioural analysis of users navigating in immersive space aimed at enabling the next-generation multimedia systems. Our main goal is to understand how user experience content with 6-Degrees-of-Freedom (DoF) affected not only by visual and its quality but also disposition user. We based our investigations on traditional statistical metrics, techniques that have been already used for 6-DoF, as well adapted 3-DoF tools be this new context. show limitation...
In recent years, a large variety of online communication tools have emerged, including social Virtual Reality (VR) platforms for interacting in virtual world with participants being represented as avatars. Given their popularity, an active area research focuses on improving the user experience these experiences. To enable experimentation at scale platforms, it is however essential to collect behavioural data (e.g. movements and audio information). this work, we present toolchain that enables...
Abstract Point clouds denote a prominent solution for the representation of 3D photo-realistic content in immersive applications. Similarly to other imaging modalities, quality predictions point cloud contents are vital wide range applications, enabling trade-off optimizations between data and size every processing step from acquisition rendering. In this work, we focus on use cases that consider human end-users consuming and, hence, concentrate visual metrics. particular, propose set...
Plenoptic content is becoming increasingly popular thanks to the availability of acquisition and display devices. Thanks image-based rendering techniques, a plenoptic can be rendered in real time an interactive manner allowing virtual navigation through captured scenes. This way consumption enables new experiences, therefore introduces several challenges terms data processing, transmission consequently visual quality evaluation. In this paper, we propose methodology subjectively assess...
In recent years, the research community has witnessed a growing interest in immersive representations of real world, such as light field. However, due to increased volume data generated acquisition, new and efficient compression algorithms are needed store deliver field contents. A Grand Challenge on image coding was organised during ICIP 2017 collect evaluate for lenslet-based images. This paper reports results objective subjective evaluation campaign conducted assess responses grand...
Real-time, immersive telecommunication systems are quickly becoming a reality, thanks to the advances in acquisition, transmission, and rendering technologies. Point clouds particular serve as promising representation these type of systems, offering photorealistic capabilities with low complexity. Further development coding, quality evaluation algorithms, though, is currently hindered by lack publicly available datasets that represent realistic scenarios remote communication between people...
A computationally-simplified and descriptor-richer Point Cloud Quality Assessment (PCQA) metric, namely Point-PCA+, is proposed in this paper, which an extension of PointPCA. PointPCA a set perceptually-relevant descriptors based on PCA decomposition that were applied to both the geometry texture data point clouds for full reference PCQA. PointPCA+ employs only while enriching existing descriptors, are computed more efficiently. Similarly PointPCA, total quality score obtained through...
The recent advances in light field imaging are changing the way which visual content is captured, processed and consumed. Storage delivery systems for images rely on efficient compression algorithms. Such algorithms must additionally take into account feature-rich rendering content. Therefore, a proper evaluation of quality essential to design improve coding solutions Consequently, subjective tests should also reflect process. This paper aims at presenting comparing two methodologies assess...
Technological advances in head-mounted displays and novel real-time 3D acquisition reconstruction solutions have fostered the development of 6 Degrees Freedom (6DoF) teleimmersive systems for social VR applications. Point clouds emerged as a popular format such applications, owing to their simplicity versatility; yet, dense point cloud contents are too large deliver directly over bandwidth-limited networks. In this context, user-adaptive delivery mechanisms promising solution exploit...