SIDIRE: Synthetic Image Dataset for Illumination Robustness Evaluation
收藏资源简介：
SIDIRE is a freely available image dataset which provides synthetically generated images allowing to investigate the influence of illumination changes on object appearance. The images are renderings of 3D coin models with different material BRDFs and levels of texturedness. Thus, the dataset makes it possible to directly evaluate the influence of these conditions on the performance of image recognition without introducing a bias due to different objects used between image sets. The dataset has been used for evaluation in [1]. <strong>Usage</strong> The dataset is freely available for non-commercial research use. Please cite our paper [1] when using the dataset for your research. <strong>Technical Details</strong> Full Image Dataset The full image dataset consists of images of 14 coin models which have been rendered using the open-source graphics software Blender. For each model, twelve sets of 500×500 images with 65 illumination directions were rendered where each set represents one out of four material BRDFs and one out of three texture density levels. Material BRDFs are intended to represent different levels of specularity starting from a Lambertian material with zero specularity up to specular intensity values of 0.25, 0.50 and 1.00. The first texture density level shows no texture and thus represents the set of textureless objects. For the remaining two levels synthetically generated textures were used. The camera image plane is placed parallel to the coin and light source positions are defined by their azimuth angle φ and elevation angle λ. We used eight levels of λ with eight levels of φ each to produce 64 images. The 65th image is rendered with the light placed at the camera position (i.e. λ=90°).<br> In the provided RAR-file, all the 65 images of a specific model, specularity level and texturedness level are contained in separate directories. For instance, the directory ‘texture_level0\Ref_level2\2874-back’ contains the images of the model ‘2874-back’ rendered without texture and a specularity of 0.50. <strong>Patch Dataset</strong> The patch dataset contains 50000 matching patch pairs for every of the 12 subsets of SIDIRE. It can be used to generate groups of feature distances by means of true and false patch pairs, in the same manner as, e.g., Matthew Brown’s patch dataset. Please see [1,2] for a detailed description of the evaluation scheme of patch pair databases.<br> The patches have a size of 64×64 and are arranged in images of size 3200×3200. Thus, every image contains 2500 patches where corresponding patches are placed side by side. The patches of the 12 subsets are contained in directories indicating their texture density and reflectance level, e.g. patches rendered without texture and a specularity of 0.50 are contained in the directory ‘tex0_ref2’.<br> <strong>References</strong> [1] Zambanini S., Kampel M. “Evaluation of Low-Level Image Representations for Illumination-Insensitive Recognition of Textureless Objects”, <em>International Conference on Image Analysis and Processing – ICIAP’13</em>, Naples, Italy, September 2013. (pdf, supplementary material)<br> [2] Brown, M., Gang Hua, Winder, S., “Discriminative Learning of Local Image Descriptors”, <em>Pattern Analysis and Machine Intelligence, </em> vol.33, no.1, pp.43-57, 2011.
SIDIRE是一款可免费获取的图像数据集，旨在通过合成生成的图像，探究光照变化对物体外观的影响。该数据集的图像均为采用不同材质双向反射分布函数（BRDF）与纹理复杂度等级的3D硬币模型的渲染结果。因此，本数据集可直接评估上述条件对图像识别性能的影响，且不会因不同图像集采用不同物体而引入评估偏差。本数据集已被文献[1]用于相关评估工作。 使用说明 本数据集仅可免费用于非商业性研究工作。若将本数据集用于您的研究，请引用本文献[1]。 技术细节 完整图像数据集 完整图像数据集包含14款硬币模型的渲染图像，均通过开源图形软件Blender生成。针对每一款模型，我们渲染了12组分辨率为500×500的图像，每组包含65个光照方向的渲染结果；每组图像分别对应4种材质BRDF与3种纹理密度等级中的一种组合。 材质BRDF用于表征不同的镜面反射等级，从无镜面反射的朗伯（Lambertian）材质，到镜面反射强度分别为0.25、0.50与1.00的材质。第一级纹理密度无任何纹理，对应无纹理物体；其余两级则采用合成生成的纹理。 相机成像平面与硬币保持平行，光源位置由方位角φ与仰角λ确定。我们通过8档仰角λ与每档8档方位角φ生成了64张图像；第65张图像的光源位于相机位置（即λ=90°）。 在提供的RAR压缩包中，特定模型、镜面反射等级与纹理等级对应的全部65张图像均存放在独立的目录中。例如，目录'texture_level0Ref_level22874-back'内存储的是无纹理且镜面反射强度为0.50的'2874-back'模型的渲染图像。 图像块数据集 图像块数据集为SIDIRE的12个子集各提供了50000对匹配图像块。可借助正、负图像块对生成特征距离组，其使用方式与Matthew Brown的图像块数据集类似。有关图像块对数据库的评估方案的详细说明，请参阅文献[1,2]。 图像块的尺寸为64×64，排布于3200×3200分辨率的图像中；因此每张图像包含2500个图像块，且匹配的图像块彼此相邻放置。12个子集的图像块均存放在标注了纹理密度与反射等级的目录中，例如无纹理且镜面反射强度为0.50的图像块存放在目录'tex0_ref2'内。 参考文献 [1] Zambanini S.、Kampel M.：《面向无纹理物体光照不敏感识别的低层图像表征评估》，发表于《国际图像分析与处理会议（ICIAP’13）》，意大利那不勒斯，2013年9月。（含PDF与补充材料） [2] Brown M.、Gang Hua、Winder S.：《局部图像描述符的判别式学习》，发表于《模式分析与机器智能汇刊》，第33卷第1期，第43-57页，2011年。
