ULB Plenoptic 2.0 Raytrix R8 Video with Single Moving Camera: DeerComplexToys, part 1

<p><strong>ULB Plenoptic 2.0 Raytrix R8 Video with Single Moving Camera: DeerComplexToys, Part 1</strong></p> <p>The test sequence "ULB Plenoptic 2.0 Raytrix R8 Video with Single Moving Camera: DeerComplexToys, Part 1" is provided by Daniele Bonatto, Sarah Fachada, Hamed Razavi Khosroshahi, Gauthier Lafruit, and Mehrdad Teratani, members of the LISA department, EPB (Ecole Polytechnique de Bruxelles), ULB (Universit&eacute; Libre de Bruxelles), Belgium.</p> <p><strong>&nbsp;</strong></p> <p><strong>License:</strong></p> <p>CC BY-NC-SA</p> <p><strong>&nbsp;</strong></p> <p><strong>Terms of Use:</strong></p> <p>Any kind of publication or report using this sequence should refer to the following reference:</p> <p>[1] Sarah Fachada, Daniele Bonatto, Hamed Razavi Khosroshahi, Gauthier Lafruit, and Mehrdad Teratani, "ULB Plenoptic 2.0 Raytrix R8 Video with Single Moving Camera: DeerComplexToys, Part 1" 2024.07, 10.5281/zenodo.12546958.</p> <p><code>@misc{bonatto_ulb_deercomplextoys_moving_2024,</code><br><code>&nbsp; &nbsp; title = {{ULB} {Plenoptic} 2.0 {Raytrix} {R8} {Video} with {Single} {Moving} {Camera}: {DeerComplexToys}, {Part} 1},</code><br><code>&nbsp; &nbsp; author = {Bonatto, Daniele and Fachada, Sarah and Razavi Khosroshahi, Hamed, and Lafruit, Gauthier and Teratani, Mehrdad},</code><br><code>&nbsp; &nbsp; month = jul,</code><br><code>&nbsp; &nbsp; year = {2024},</code><br><code>&nbsp; &nbsp; doi = {10.5281/zenodo.12546958}</code><br><code>}</code></p> <p><strong>&nbsp;</strong></p> <p><strong>Production:</strong></p> <p>Laboratory of Image Synthesis and Analysis, LISA department, Ecole Polytechnique de Bruxelles, Universit&eacute; Libre de Bruxelles, Belgium.</p> <p>&nbsp;</p> <p><strong>Content:</strong></p> <p>This dataset contains a dynamic scene featuring moving toys captured with a Raytrix R8 camera [1].</p> <p>The dataset is split in two Zenodo links:</p> <p>10.5281/zenodo.12546958 (this, sequences 0-2)</p> <p>10.5281/zenodo.12668349 (sequences 3,4)</p> <p>The dataset is separated into five different sequences of 300 frames each:</p> <p>1.&nbsp;<strong>Sequence 0:</strong></p> <p>&nbsp;&nbsp;&nbsp;&nbsp;- A mix of a non-moving camera for about half of the video, followed by the camera starting to move in a linear fashion.</p> <p>2. <strong>Sequences 1 to 4:</strong></p> <p>&nbsp;&nbsp;&nbsp;&nbsp;- The same video split into 300 frames each, starting only when the camera begins its movement.</p> <p><strong>&nbsp;</strong></p> <p>Additionally, the dataset includes a grid of views and calibration images captured with the plenoptic camera under the same lighting conditions. These calibration images include views of a chessboard rotated in several positions.</p> <p>The sequences consist of a linear movement of the camera, the images are named R8-C-A-U3-B028-RS-A - 2081_000000000X_Processed.png, where the X represent the frame number.</p> <p>The grid follow the format of `X{x position}_Y{x position}_Processed.png` it is composed of images acquired between x=0 and x=20 by steps of 5cm and y=00 and y=100 by steps of 10cm.</p> <p>Calibration files are provided in XML format. The datasets were acquired with a robotic bench made at ULB [2][3].</p> <p><strong>&nbsp;</strong></p> <p><strong>The dataset contains:</strong></p> <p>- `sequences` zip files containing:</p> <p>&nbsp;&nbsp;- one zip file for each sequence, with plenoptic images in PNG format.</p> <p>&nbsp;&nbsp;- XML calibration files.</p> <p>- A `grid` folder containing:</p> <p>&nbsp;&nbsp;- Plenoptic images in PNG format of the grid views.</p> <p>&nbsp;&nbsp;- XML calibration files.</p> <p>- A `checkerboard` folder containing:</p> <p>&nbsp;&nbsp;- Plenoptic raw images in PNG format of the checkerboard in various positions.</p> <p>&nbsp;&nbsp;- XML calibration files.</p> <p><strong>&nbsp;</strong></p> <p><strong>References and links:</strong></p> <p>[1] <a href="https://raytrix.de/">https://raytrix.de/</a></p> <p>[2] D. Bonatto, A. Schenkel, T. Lenertz, Y. Li, et G. Lafruit, &laquo; [MPEG-I Visual] ULB High Density 2D/3D Camera Array data set, version 2 [m41083] &raquo;, in ISO/IEC JTC1/SC29/WG11 MPEG2017/M41083, Torino, Italy, juill. 2017.</p> <p>[3] D. Bonatto, &laquo; From multi-modal capture to photo-realistic view synthesis - A high-quality and real-time multiview approach &raquo;, 2024.</p> <p><strong>&nbsp;</strong></p> <p><strong>Acknowledgments:</strong></p> <p>Sarah Fachada is a Postdoctoral Researcher of the Fonds de la Recherche Scientifique - FNRS, Belgium. This work was supported in part by the HoviTron project (no. 951989), the FER 2021 project (no. 1060H000066-FAISAN), the Emile DEFAY 2021 project (no. 4R00H000236), and the FER 2023 project (no. 1060H000075).</p>