1,721,444 research outputs found
Studie van Beelscanningsmechanismen voor een snellere Beeldverwerking -- Ingénieur civil
No full textinfo:eu-repo/semantics/nonPublishe
A Scalable End-to-End Optimized Real-Time Image-Based Rendering Framework on Graphics Hardware
No full textThis paper presents the system-level overview of a real-time image-based rendering framework performing multiple intermediate view synthesis, completely on the Graphics Processing Unit (GPU). The software design achieves high-performance, yet maintains flexibility and ease of development through a hierarchical layered architecture. The framework implements the intermediate view synthesis by a chain of consecutive processing modules, as an extension to the Middlebury open software structure, allowing it to benchmark quality and execution time of individual modules for end-to-end system performance optimization. The modules can be flexibly coordinated, enabling scalability to run the multiple view synthesis in real-time on both powerful and weak GPUs
A High-level Kernel Transformation Rule Set for Efficient Caching on Graphics Hardware - Increasing Streaming Execution Performance with Minimal Design Effort
No full textThis paper proposes a high-level rule set that allows algorithmic designers to optimize their implementation on graphics hardware, with minimal design effort. The rules suggest possible kernel splits and merges to transform the kernels of the original design, resulting in an inter-kernel rather then low-level intra-kernel optimization. The rules consider both traditional texture caches and next-gen shared memory – which are used in the abstract stream-centric paradigms such as CUDA and Brook+ – and can therefore be implicitly applied in most generic streaming applications on graphics hardware
A High-level Kernel Transformation Rule Set for Efficient Caching on Graphics Hardware - Increasing Streaming Execution Performance with Minimal Design Effort
No full textThis paper proposes a high-level rule set that allows algorithmic designers to optimize their implementation on graphics hardware, with minimal design effort. The rules suggest possible kernel splits and merges to transform the kernels of the original design, resulting in an inter-kernel rather then low-level intra-kernel optimization. The rules consider both traditional texture caches and next-gen shared memory – which are used in the abstract stream-centric paradigms such as CUDA and Brook+ – and can therefore be implicitly applied in most generic streaming applications on graphics hardware
A Scalable End-to-End Optimized Real-Time Image-Based Rendering Framework on Graphics Hardware
No full textThis paper presents the system-level overview of a real-time image-based rendering framework performing multiple intermediate view synthesis, completely on the Graphics Processing Unit (GPU). The software design achieves high-performance, yet maintains flexibility and ease of development through a hierarchical layered architecture. The framework implements the intermediate view synthesis by a chain of consecutive processing modules, as an extension to the Middlebury open software structure, allowing it to benchmark quality and execution time of individual modules for end-to-end system performance optimization. The modules can be flexibly coordinated, enabling scalability to run the multiple view synthesis in real-time on both powerful and weak GPUs
RabbitStamp Test Sequence
No full text# RabbitStamp sequence by LISA ULB
The test sequence "RabbitStamp" is provided by Sarah Fachada, Yupeng Xie, Daniele Bonatto, Gauthier Lafruit, Mehrdad Teratani, members of the LISA department, EPB (Ecole Polytechnique de Bruxelles), ULB (Universite Libre de Bruxelles), Belgium.
# License:
CC BY-NC-SA
ONLY Available for Academic Usage
# Terms of Use:
Anykind of publication or report using this sequence should refer to the following references.
[1] Sarah Fachada, Yupeng Xie, Daniele Bonatto, Gauthier Lafruit, Mehrdad Teratani, "RabbitStamp Test Sequence", 2021.
@misc{fachada_RabbitStamp_2021,
title = {{RabbitStamp} {Test} {Sequence}},
author = {Fachada, Sarah and Xie; Yupeng and Bonatto, Daniele and Lafruit, Gauthier and Teratani, Mehrdad },
month = jul,
year = {2021},
doi = {10.5281/zenodo.5053771}
}
[2] Sarah Fachada, Yupeng Xie, Daniele Bonatto, Gauthier Lafruit, Mehrdad Teratani, "[DLF] Plenoptic 2.0 Multiview Lenslet Dataset and Preliminary Experiments [m56429]", 2021.
@article{fachada_RabbitStamp_2021,
title = {[DLF] {Plenoptic} 2.0 {Multiview} {Lenslet} {Dataset} and {Preliminary} {Experiments} [m56429]},
author = {Fachada, Sarah and Xie; Yupeng and Bonatto, Daniele and Lafruit, Gauthier and Teratani, Mehrdad },
journal = {ISO/IEC JTC1/SC29/WG11},
month = apr,
year = {2021}
}
[3] Sarah Fachada, Yupeng Xie, Daniele Bonatto, Gauthier Lafruit, Mehrdad Teratani, "[LVC] Update for RabbitStamp: Plenoptic 2.0 Multiview Lenslet Dataset [m57100]", 2021.
@article{fachada_RabbitStamp_2021,
title = {[LVC] {Update} for {RabbitStamp}: {Plenoptic} 2.0 {Multiview} {Dataset} [m56429]},
author = {Fachada, Sarah and Xie; Yupeng and Bonatto, Daniele and Lafruit, Gauthier and Teratani, Mehrdad },
journal = {ISO/IEC JTC1/SC29/WG11},
month = jul,
year = {2021}
}
[4] Sarah Fachada, Yupeng Xie, Daniele Bonatto, Gauthier Lafruit, Mehrdad Teratani, "[LVC] Exploration Experiments using RabbitStamp Multiview Lenslet Images [m57101]", 2021.
@article{fachada_RabbitStamp_2021,
title = {[LVC] {Exploration} {Experiments} {Using} {RabbitStamp} {Multiview} {Lenslet} {Images} [m56429]},
author = {Fachada, Sarah and Xie; Yupeng and Bonatto, Daniele and Lafruit, Gauthier and Teratani, Mehrdad},
journal = {ISO/IEC JTC1/SC29/WG11},
month = jul,
year = {2021}
}
# Production:
Laboratory of Image Synthesis and Analysis, LISA department, Ecole Polytechnique de Bruxelles, Universite Libre de Bruxelles, Belgium.
# Content:
This dataset contains a test scene acquired with a raytrix camera [1] array of 7x3 views. For details of the dataset, please refer to the references mentioned above.
The dataset contains:
- a `depth_7x3_center` depth maps computed with DERS reference software [2] in yuv40016ble format and json configuration files to do so,
- a `multiview_7x3_5x5_images` Calibrated subimages computed with RLC [3] in yuv42010ble format, the cameras.json with the camera parameters and view_synthesis.json with the view synthesis experiment.
- a `multiview_7x3_lenslets` folder containing the lenslet views in yuv42010ble format, the Raytrix xml calibration file and RLC cfg file for conversion to multiview.
# References and links:
[1] Raytrix, https://raytrix.de/
[2] S. Rogge and D. Bonatto and J. Sancho and R. Salvador and E. Juarez and A. Munteanu and G. Lafruit, "MPEG-I Depth Estimation Reference Software", in 2019 International Conference on 3D Immersion (IC3D), 2019.
[3] M. Teratani and T. Fujii, "[MPEG-I Visual] Conversion of Lenslet Data Capture by Single Focussed Plenoptic Camera to Multiview Video using RLC0.3 [N18567]", ISO/IEC JTC1/SC29/WG11, 201
Biological-Aware Stereoscopic Rendering in Free Viewpoint Technology using GPU Computing
No full textIn this paper we present a biological-aware stereoscopic renderer that is used in a video communication system, to convincingly provide the participants with synthetic 3D perception. As opposed to conventional 3D systems - where pre-recorded content is presented to the viewer without taking his or her viewing location into account - we adaptively exploit both monocular and binocula cues of the human vision system, based on the viewing location. By using a GPU-based control loop, we are able to provide real-time synthetic 3D perception that is experienced as being rich and natural, without losing any visual comfort whatsoever
Stream-Centric Stereo Matching and View Synthesis: A High-Speed Approach on GPUs
No full textIn this paper, we propose a real-time image-based rendering (IBR) system. It is specifically designed for photorealistic view synthesis at high-speed on the graphics processing unit (GPU). We steer the proposed IBR system design with two high-level ideas. First, for cost-effective IBR, as long as the synthesized views look visually plausible, the estimated disparity and occlusion need not be correct. Hence, we jointly optimize stereo matching and view synthesis for a favorable end-to-end performance. Second, for great real-time acceleration on GPUs, all functional modules need be shaped at an early design stage, fitting the massively parallel streaming architecture of GPUs. Based on these two guidelines, we first propose a stream-centric local stereo matching algorithm. The key idea is to construct a versatile set of variable support patterns in a highly efficient manner, and then an optimal local support pattern is selected to approximate varying image structures adaptively. Next, a low-complexity adaptive view synthesis technique is proposed. It efficiently tackles visual artifacts in synthesized images, using a novel photometric outlier detection and handling scheme. We evaluated both the disparity estimation accuracy and novel view synthesis quality of the proposed approach, based on the benchmark Middlebury stereo datasets. The experiments show that our local stereo method produces consistently reliable disparity estimates for both homogeneous regions and depth discontinuities, outperforming several previous GPU-based local methods. More importantly, visually plausible intermediate views are generated by our IBR approach at high-speed on the GPU. With stereo matching and view synthesis completely running on an NVIDIA GeForce 8800 GT graphics card, the proposed IBR system reaches about 100 f/s for 450x375 stereo images with 60 disparity levels
COMPLEXITY REDUCTION OF REAL-TIME DEPTH SCANNING ON GRAPHICS HARDWARE
No full textThis paper presents an intelligent control loop add-on to reduce the total amount of hardware operations - and therefore the resulting execution speed - of a real-time depth scanning algorithm. The analysis module of the control loop predicts redundant brute-force operations, and dynamically adjusts the input parameters of the algorithm, to avoid scanning in a space that lacks the presence of objects. Therefore, this approach reduces the algorithmic complexity in proportion with the amount of void within the scanned volume, while remaining fully compliant with stream-centric paradigms such as CUDA and Brook+
Immersive GPU-driven biological adaptive stereoscopic rendering
No full textIn this paper, we want to sensitize 3D content developers
and researchers of broadening their scope of parameters
they take into account for generating 3D content. State-of-theart perceptual research has already shown that monocular visual cues highly contribute to the very fundamentals of 3D perception, and binocular ones are merely linked to them in order to create a rich depth experience. In this context, we present an overview
of the research concerning our teleconferencing system that is able to recreate biological stereoscopic input, without loosing consistency in all related monocular cues such as accommodation, occlusion, size (gradient), motion parallax, texture gradient and linear perspective. The system adapts in real-time by doing both GPU-driven analysis and rendering, based on the physical parameters of the system user
- …
