ShapeNet Intrinsic Images v2.0 Extended

The synthetic ShapeNet intrinsic image decomposition dataset of 90,000 images. 50,000 of them were used for training the deep CNN models of CVIU'2021 - see Section 4 of the paper. This is the extension of the first release of the synthetic ShapeNet intrinsic image decomposition dataset of 20,000 images used for training the deep CNN models IntrinsicNet and RetiNet of CVPR'2018. See Section 4.1 of the CVPR paper for the details of the data rendering. Similar to the initial dataset, both albedo and shading ground-truth images were in HDR, and later normalized to [0,1] using min-max. Then, the composite RGB image was created by element-wise multiplying the related albedo and shading ground truths. - albedo -> albedo (reflectance) ground-truth images [8bits] - shading -> gray-scale shading (illumination) ground-truth images [8bits] - mask -> object masks [binary] - composite -> composite RGB image (albedo x shading) [16bits] - shading_prior_initial -> initial sparse shading estimations (see Section 3.3 of the paper) [8bits] - shading_prior_filled -> dense shading map reconstruction (see Section 3.4 of the paper) [16bits] shading_prior_filled folder is split into two parts (shading_prior_filled.z01 and shading_prior_filled.zip). To extract them, you need to unzip. If you are not sure how, check this link https://superuser.com/a/336224 Note that the prefixes of the file names (ambient, test_not_used and with_normals) do not indicate anything extra.本数据集为包含90000张图像的合成ShapeNet本征图像分解数据集。其中50000张图像用于训练CVIU 2021的深度卷积神经网络（CNN）模型，详见论文第4节。本数据集是2018年CVPR会议中用于训练IntrinsicNet与RetiNet深度CNN模型的20000张合成ShapeNet本征图像分解数据集首次发布版本的扩展版本。有关数据渲染的细节，请参阅该CVPR论文的第4.1节。与初始数据集一致，本次发布的反照率（albedo，反射率）与光照（shading，照明）真值图像均采用高动态范围（High Dynamic Range, HDR）格式，后经最小-最大归一化至[0,1]区间。随后通过将对应反照率与光照真值逐元素相乘，生成合成RGB图像。各数据类型详情如下：- 反照率（albedo，反射率）真值图像：8位图像；- 光照（shading，照明）真值图像：灰度光照真值图像，8位；- 掩码（mask）：目标二值掩码；- 合成图像（composite）：合成RGB图像（反照率 × 光照），16位；- 初始稀疏光照估计（shading_prior_initial）：详见论文第3.3节，8位图像；- 稠密光照图重建结果（shading_prior_filled）：详见论文第3.4节，16位图像。shading_prior_filled文件夹被拆分为shading_prior_filled.z01与shading_prior_filled.zip两个分卷，需合并解压。若不清楚操作方法，可参阅该链接：https://superuser.com/a/336224。请注意，文件名前缀（ambient、test_not_used与with_normals）无额外含义。