Magritte Sphere Video

# Magritte-Sphere Video sequence by LISA ULB The test sequence "Magritte Sphere Video" 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. # License: CC BY-NC-SA # Terms of Use: Anykind of publication or report using this sequence should refer to the following references. [1] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, "Magritte Sphere Video Test Sequence", 2021. @misc{fachada_magrittevideo_2021, title = {{Magritte} {Sphere} {Video} {Test} {Sequence}}, author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier}, month = feb, year = {2021}, doi = {10.5281/zenodo.5048270} } [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} } # Production: Laboratory of Image Synthesis and Analysis, LISA department, EPB, Universite Libre de Bruxelles, Belgium. # Content: 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. The scene contains a non-Lambertian (transparent-refractive (T) or mirror-specular (M)) sphere rendered in a regular camera array of 21x21 cameras. It describes a spiral around a central initial position within 17 frames. In addition to the 3D model, we provide the rendered images : resolution of 2000x2000, the cameras are parallel, with a principal point at the center of the image. We provide 17 frames of: - a regular subarray of 5x5 cameras (cameras number 66, 70, 74, 78, 82, 50, 154, 158, 162, 166, 234, 238, 242, 246, 250, 318, 322, 326, 330, 334, 402, 406, 410, 414, 418) - the central horizontal line of 21 cameras (cameras 210 to 230) The dataset contains: - a `camera.json` file in OMAF coordinates system (Camera position: X: forwards, Y:left, Z: up, Rotation: yaw, pitch, roll) [3], - a `parameters.cfg` generated with [2], - a `texture_M` folder containing the rendered views in yuv420p10le format for the mirror object, - a `texture_T` folder containing the rendered views in yuv420p10le format for the transparent object, - a `mask` folder containing the mask indicating the sphere in yuv420p format, - a `depth_gt` folder containing the associated ground truth depth maps yuv420p16le format, - a `depth_estimated_M` folder containing the associated estimated depth maps yuv420p16le format, - a `depth_estimated_T` folder containing the associated estimated depth maps yuv420p16le format. # References and links: [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# 由LISA ULB制作的Magritte-Sphere视频序列 本测试序列“Magritte Sphere Video”由比利时布鲁塞尔自由大学（Université Libre de Bruxelles，简称ULB）布鲁塞尔高等理工学院（Ecole Polytechnique de Bruxelles，简称EPB）LISA系的Sarah Fachada、Daniele Bonatto、Mehrdad Teratani与Gauthier Lafruit提供。 # 许可协议：CC BY-NC-SA # 使用条款：任何使用该序列的出版物或报告均需引用以下参考文献。 [1] Sarah Fachada, Daniele Bonatto, Mehrdad Teratani, Gauthier Lafruit, "Magritte Sphere Video Test Sequence", 2021. @misc{fachada_magrittevideo_2021, title = {{Magritte} {Sphere} {Video} {Test} {Sequence}}, author = {Fachada, Sarah and Bonatto, Daniele and Teratani, Mehrdad and Lafruit, Gauthier}, month = feb, year = {2021}, doi = {10.5281/zenodo.5048270} [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：比利时布鲁塞尔自由大学LISA系图像合成与分析实验室（Laboratory of Image Synthesis and Analysis, LISA department, EPB, Université Libre de Bruxelles, Belgium） # 数据集内容：本数据集包含使用Blender[1]及适配Blender 2.8的扩展插件脚本[2]创建并渲染的测试场景。本团队提供Blender工程文件与渲染完成的场景文件。该场景包含一个非朗伯（non-Lambertian）材质球体，分为透明折射型（T）与镜面反射型（M）两类，通过21×21阵列的常规相机进行渲染。序列共计17帧，呈现围绕初始中心位置的螺旋运动轨迹。 除3D模型外，本团队还提供渲染图像：分辨率为2000×2000，相机为平行投影构型，主点位于图像几何中心。本次发布的17帧数据涵盖： - 5×5常规子阵列相机（相机编号：66、70、74、78、82、50、154、158、162、166、234、238、242、246、250、318、322、326、330、334、402、406、410、414、418） - 由21台相机组成的中心水平线阵列（相机编号210至230） 本数据集包含以下文件与文件夹： - 采用全向媒体格式（OMAF）坐标系的`camera.json`文件（相机位置：X轴为前方，Y轴为左侧，Z轴为上方；旋转参数：偏航、俯仰、滚转）[3] - 由[2]生成的`parameters.cfg`文件 - `texture_M`文件夹：存储镜面物体的渲染视图，格式为yuv420p10le - `texture_T`文件夹：存储透明物体的渲染视图，格式为yuv420p10le - `mask`文件夹：存储标记球体区域的蒙版，格式为yuv420p - `depth_gt`文件夹：存储对应的真值深度图，格式为yuv420p16le - `depth_estimated_M`文件夹：存储镜面物体对应的估计深度图，格式为yuv420p16le - `depth_estimated_T`文件夹：存储透明物体对应的估计深度图，格式为yuv420p16le # 参考文献与链接： [1] Blender在线社区. “Blender——一款3D建模与渲染软件包.” 阿姆斯特丹：Blender基金会Blender研究所, 2020. [2] K. Honauer、O. Johannsen、D. Kondermann与B. Goldluecke. 《面向4D光场深度估计的数据集与评估方法》，发表于2016年亚洲计算机视觉大会（Asian Conference on Computer Vision）。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