Mirror Magritte Torus Test Sequence

<p><strong>&nbsp;# Mirror-Magritte-Torus sequence by LISA ULB</strong></p> <p><br> The test sequence &quot;Mirror Magritte Torus&quot; is provided by Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, members of the LISA department, EPB (Ecole Polytechnique de Bruxelles), ULB (Universite Libre de Bruxelles), Belgium.</p> <p><strong>&nbsp;# License:</strong></p> <p><br> CC BY-NC-SA</p> <p><strong>&nbsp;# Terms of Use:</strong></p> <p><br> Anykind of publication or report using this sequence should refer to the following references.</p> <p>[1] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, &quot;Mirror Magritte Torus Test Sequence&quot;, 2021.</p> <p><em>@misc{fachada_mirror_2021,<br> &nbsp;&nbsp; &nbsp;title = {Mirror {Magritte} {Torus} {Test} {Sequence}},<br> &nbsp;&nbsp; &nbsp;author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier},<br> &nbsp;&nbsp; &nbsp;month = feb,<br> &nbsp;&nbsp; &nbsp;year = {2021},<br> &nbsp;&nbsp; &nbsp;doi = {</em>10.5281/zenodo.5048262<em>}<br> }</em></p> <p>[2] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, and Gauthier Lafruit, &quot;Light Field Rendering for non-Lambertian Objects,&quot; presented at the Electronic Imaging, 2021.</p> <p><em>@inproceedings{fachada_light_2021,<br> &nbsp;&nbsp; &nbsp;title = {Light {Field} {Rendering} for non-{Lambertian} {Objects}},<br> &nbsp;&nbsp; &nbsp;booktitle = {Electronic {Imaging}},<br> &nbsp;&nbsp; &nbsp;author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier},<br> &nbsp;&nbsp; &nbsp;year = {2021}<br> }</em></p> <p><strong>&nbsp;# Production:</strong></p> <p><br> Laboratory of Image Synthesis and Analysis, LISA department, EPB, Universite Libre de Bruxelles, Belgium.</p> <p><strong>&nbsp;# Content:</strong></p> <p><br> This dataset contains a test scene created and rendered with Blender [1] and the addon script [2] extended for Blender 2.8. We provide the Blender file and the rendered scene.</p> <p>The scene contains a mirror reflective torus rendered in a regular camera array of 21x21 cameras.</p> <p>In addition to the 3D model, we provide the images in the folder `parallel_cameras` : resolution of 2000x2000, the cameras are parallel, with a principal point at the center of the image.</p> <p>The dataset contains:<br> &nbsp;- a `camera.json` file in OMAF coordinates system (Camera position: X: forwards, Y:left, Z: up, Rotation: yaw, pitch, roll) [3],<br> &nbsp;- a `parameters.cfg` generated with [2],<br> &nbsp;- a `texture` folder containing the rendered views in png format,<br> &nbsp;- a `depth` folder containing the associated depth maps in exr format.<br> &nbsp;<br> &nbsp;<br> <strong>&nbsp;# References and links:</strong><br> &nbsp;<br> [1] Blender Online Community, &quot;Blender - a 3D modelling and rendering package.&quot; Blender Institute, Amsterdam: Blender Foundation, 2020.</p> <p>[2] K. Honauer, O. Johannsen, D. Kondermann, and B. Goldluecke, &quot;A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields&quot; in Asian Conference on Computer Vision, 2016,<br> https://github.com/lightfield-analysis/blender-addon<br> https://github.com/dbonattoj/blender-addon</p> <p>[3] B. Kroon, &quot;Reference View Synthesizer (RVS) manual [N18068],&quot; ISO/IEC JTC1/SC29/WG11, Macau SAR, China, p. 19, Oct. 2018.<br> https://mpeg.chiariglione.org/standards/mpeg-i/omnidirectional-media-format</p> <p>&nbsp;</p> <p>&nbsp;</p>