1. |
- Ak, Ali, et al.
(författare)
-
BASICS: Broad Quality Assessment of Static Point Clouds in a Compression Scenario
- 2024
-
Ingår i: IEEE transactions on multimedia. - : Institute of Electrical and Electronics Engineers (IEEE). - 1520-9210 .- 1941-0077. ; 26, s. 6730-6742
-
Tidskriftsartikel (refereegranskat)abstract
- Point clouds have become increasingly prevalent in representing 3D scenes within virtual environments, alongside 3D meshes. Their ease of capture has facilitated a wide array of applications on mobile devices, from smartphones to autonomous vehicles. Notably, point cloud compression has reached an advanced stage and has been standardized. However, the availability of quality assessment datasets, which are essential for developing improved objective quality metrics, remains limited. In this paper, we introduce BASICS, a large-scale quality assessment dataset tailored for static point clouds. The BASICS dataset comprises 75 unique point clouds, each compressed with four different algorithms including a learning-based method, resulting in the evaluation of nearly 1500 point clouds by 3500 unique participants. Furthermore, we conduct a comprehensive analysis of the gathered data, benchmark existing point cloud quality assessment metrics and identify their limitations. By publicly releasing the BASICS dataset, we lay the foundation for addressing these limitations and fostering the development of more precise quality metrics.
|
|
2. |
- Alain, Martin, et al.
(författare)
-
Introduction to Immersive Video Technologies
- 2023. - 1
-
Ingår i: Immersive Video Technologies. - Cambridge, Massachusetts, USA : Academic Press. - 9780323917551 - 9780323986236 ; , s. 3-24
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- Immersive imaging technologies have become a topic of great interest in recent years due to the convergence of maturing research from different fields and broad aspects of signal and image processing, including but not limited to: computer vision, computer graphics, computational imaging, optics, and recent advances in deep learning. In particular, recent research and developments in these areas helped achieve better or faster content creation and image/video processing. This enables the design of complete practical systems covering capture to display for immersive imaging. In this chapter, we provide the theoretical background for the rest of the book and introduce key concepts commonly used for traditional imaging systems and immersive video technologies. We also describe the stages of the immersive imaging technologies from content capture to display and quality assessment for three immersive imaging technologies: omnidirectional video, light fields, and volumetric (also known as free-viewpoint) video.
|
|
3. |
- Alexiou, Evangelos, et al.
(författare)
-
Subjective and Objective Quality Assessment for Volumetric Video
- 2023. - 1
-
Ingår i: Immersive Video Technologies. - Cambridge, Massachusetts, USA : Academic Press. - 9780323917551 - 9780323986236 ; , s. 501-552
-
Bokkapitel (refereegranskat)abstract
- Volumetric video (VV) is a novel form of video that allows recreation of real-world scenes in 3D with users consuming the content from any viewpoint they desire. This makes VV best suited for augmented reality (AR) or virtual reality (VR) applications. This freedom necessitates increased user interaction with the VV itself, which brings new challenges to its visual quality assessment. In this chapter, various aspects of VV quality assessment using subjective user studies and objective quality estimation methods are discussed. These aspects include the way or representing 3D models, mode of interaction, display settings (e.g., whether AR or VR headsets are used), rendering parameters, and how the characteristics of point clouds or meshes are used in quality estimation. The chapter discusses the advantages and disadvantages of different methods and provides take away messages for researchers.
|
|
4. |
- Gond, Manu, 1997-, et al.
(författare)
-
LFSphereNet : Real Time Spherical Light Field Reconstruction from a Single Omnidirectional Image
- 2023
-
Ingår i: Proceedings of the 20th ACM SIGGRAPH European Conference on Visual Media Production. - New York, NY, United States : Association for Computing Machinery (ACM). - 9798400704260 ; , s. 1-10
-
Konferensbidrag (refereegranskat)abstract
- Recent developments in immersive imaging technologies have enabled improved telepresence applications. Being fully matured in the commercial sense, omnidirectional (360-degree) content provides full vision around the camera with three degrees of freedom (3DoF). Considering the applications in real-time immersive telepresence, this paper investigates how a single omnidirectional image (ODI) can be used to extend 3DoF to 6DoF. To achieve this, we propose a fully learning-based method for spherical light field reconstruction from a single omnidirectional image. The proposed LFSphereNet utilizes two different networks: The first network learns to reconstruct the light field in cubemap projection (CMP) format given the six cube faces of an omnidirectional image and the corresponding cube face positions as input. The cubemap format implies a linear re-projection, which is more appropriate for a neural network. The second network refines the reconstructed cubemaps in equirectangular projection (ERP) format by removing cubemap border artifacts. The network learns the geometric features implicitly for both translation and zooming when an appropriate cost function is employed. Furthermore, it runs with very low inference time, which enables real-time applications. We demonstrate that LFSphereNet outperforms state-of-the-art approaches in terms of quality and speed when tested on different synthetic and real world scenes. The proposed method represents a significant step towards achieving real-time immersive remote telepresence experiences.
|
|
5. |
-
Immersive Video Technologies
- 2023. - 1
-
Samlingsverk (redaktörskap) (refereegranskat)abstract
- From capture to representation, coding, and display, video technologies have been evolving significantly and in many different directions over the last few decades, with the ultimate goal of providing a truly immersive experience to users. After setting up a common background for these technologies, based on the plenoptic function theoretical concept, Immersive Video Technologies offers a comprehensive overview of the leading technologies enabling visual immersion, including omnidirectional (360 degrees) video, light fields, and volumetric video. Following the critical components of the typical content production and delivery pipeline, the book presents acquisition, representation, coding, rendering, and quality assessment approaches for each immersive video modality. The text also reviews current standardization efforts and explores new research directions.
|
|
6. |
|
|