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 (Ecole Polytechnique de Bruxelles), ULB (Universite Libre de Bruxelles), Belgium. <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**《透明马格利特》测试序列（ULB-LISA实验室出品）** 本测试序列"透明马格利特"由比利时布鲁塞尔自由大学（Université Libre de Bruxelles，简称ULB）布鲁塞尔综合理工学院（Ecole Polytechnique de Bruxelles，简称EPB）LISA实验室的Sarah Fachada、Daniele Bonatto、Mehrdad Teratani与Gauthier Lafruit共同提供。 **授权协议：** CC BY-NC-SA（知识共享署名-非商业性使用-相同方式共享） **使用条款：** 任何使用该序列的出版物或研究报告均需引用如下参考文献。 [1] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, "Transparent Magritte Test Sequence", 2021. @misc{fachada_transparent_2021, title = {Transparent {Magritte} {Test} {Sequence}}, author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier}, month = feb, year = {2021}, doi = {10.5281/zenodo.4488243} } [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, title = {Light {Field} {Rendering} for non-{Lambertian} {Objects}}, booktitle = {Electronic {Imaging}}, author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier}, year = {2021} } **制作方：** 图像合成与分析实验室（LISA实验室），布鲁塞尔综合理工学院（EPB），布鲁塞尔自由大学（ULB），比利时。 **数据集内容：** 本数据集包含使用Blender（3D建模与渲染软件）及适配Blender 2.8的扩展插件脚本制作并渲染的测试场景，我们提供了Blender源文件与渲染完成的场景文件。该场景包含一个透明折射环面，采用21×21规格的常规相机阵列进行渲染。 除3D模型文件外，本数据集还包含两个子文件夹： - `centered_cameras`：分辨率为1000×1000，相机均以该折射环面为中心布设。 - `parallel_cameras`：分辨率为2000×2000，相机采用平行投影模式，主点位于图像中心。 每个子文件夹均包含以下内容： - `camera.json`：采用OMAF（全向媒体格式，Omnidirectional Media Format）坐标系的相机参数文件（相机坐标系定义：X轴为前进方向，Y轴为左侧方向，Z轴为向上方向；旋转参数为偏航（yaw）、俯仰（pitch）、滚转（roll））[3]。 - `parameters.cfg`：由参考文献[2]生成的参数配置文件。 - `texture`文件夹：存储PNG格式的渲染视图。 - `depth`文件夹：存储EXR格式的关联深度图。 **参考文献与链接：** [1] Blender在线社区，《Blender——一款3D建模与渲染软件》，阿姆斯特丹：Blender基金会，2020。 [2] K. Honauer、O. Johannsen、D. Kondermann与B. Goldluecke，《面向4D光场的深度估计数据集与评估方法》，收录于2016年亚洲计算机视觉大会，相关链接：https://github.com/lightfield-analysis/blender-addon、https://github.com/dbonattoj/blender-addon [3] B. Kroon，《参考视图合成器（RVS）手册[N18068]》，ISO/IEC JTC1/SC29/WG11，中国澳门特别行政区，第19页，2018年10月，相关链接：https://mpeg.chiariglione.org/standards/mpeg-i/omnidirectional-media-format