Transparent Magritte Test Sequence

<strong>Transparent-Magritte sequence by LISA ULB</strong> The test sequence "Transparent Magritte" is provided by Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, members of the LISA department, EPB, ULB. <strong> License:</strong> CC BY-NC-SA <strong> Terms of Use:</strong> Anykind of publication or report using this sequence should refer to the following references. <br> [1] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, "Transparent Magritte Test Sequence", 2021. @misc{fachada_transparent_2021,<br> title = {Transparent {Magritte} {Test} {Sequence}},<br> author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier},<br> month = feb,<br> year = {2021},<br> doi = {10.5281/zenodo.4488243}<br> } [2] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, and Gauthier Lafruit, "Light Field Rendering for non-Lambertian Objects," presented at the Electronic Imaging, 2021. @inproceedings{fachada_light_2021,<br> title = {Light {Field} {Rendering} for non-{Lambertian} {Objects}},<br> booktitle = {Electronic {Imaging}},<br> author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier},<br> year = {2021}<br> } <strong> Production</strong> Laboratory of Image Synthesis and Analysis, LISA department, EPB, Universite Libre de Bruxelles, Belgium. <strong>Content:</strong> 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 Bblender file and the rendered scene. The scene contains a transparent refractive torus rendered in a regular camera array of 21x21 cameras.<br> In addition to the 3D model, two folders are available:<br> - `centered_cameras` resolution of 1000x1000, the cameras are centered on the refractive torus.<br> - `parallel_cameras` resolution of 2000x2000, the cameras are parallel, with a principal point at the center of the image.<br> Each of these folders contains:<br> - a `camera.json` file in OMAF coordinates system (Camera position: X: forwards, Y:left, Z: up, Rotation: yaw, pitch, roll) [3],<br> - a `parameters.cfg` generated with [2],<br> - a `texture` folder containing the rendered views in png format,<br> - a `depth` folder containing the associated depth maps in exr format.<br> <br> <strong> References and links:</strong> [1] Blender Online Community, "Blender - a 3D modelling and rendering package." Blender Institute, Amsterdam: Blender Foundation, 2020. [2] K. Honauer, O. Johannsen, D. Kondermann, and B. Goldluecke, "A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields" in Asian Conference on Computer Vision, 2016, https://github.com/lightfield-analysis/blender-addon https://github.com/dbonattoj/blender-addon [3] B. Kroon, "Reference View Synthesizer (RVS) manual [N18068]," ISO/IEC JTC1/SC29/WG11, Macau SAR, China, p. 19, Oct. 2018. https://mpeg.chiariglione.org/standards/mpeg-i/omnidirectional-media-format