The datasets include 3D object models and training/test RGB-D images annotated with ground-truth 6D object poses, 2D bounding boxes and 2D binary masks. The 3D object models were created manually or using KinectFusion-like systems for 3D reconstruction. Training images were either captured by an RGB-D/Gray-D sensor or obtained by rendering the 3D object models. All test images are real. Intrinsic camera parameters are available.
The datasets are provided in the BOP format. The BOP toolkit expects all datasets to be stored in the same folder, each dataset in a subfolder named with the base name of the dataset (e.g. "lm", "lmo", "tless"). The example below shows how to download and unpack one of the datasets (LM) from bash (names of archives with the other datasets can be seen in the download links below):
export SRC=https://bop.felk.cvut.cz/media/data/bop_datasets wget $SRC/lm_base.zip # Base archive with dataset info, camera parameters, etc. wget $SRC/lm_models.zip # 3D object models. wget $SRC/lm_test_all.zip # All test images ("_bop19" for a subset used in the BOP Challenge 2019/2020). wget $SRC/lm_train_pbr.zip # PBR training images (rendered with BlenderProc4BOP). unzip lm_base.zip # Contains folder "lm". unzip lm_models.zip -d lm # Unpacks to "lm". unzip lm_test_all.zip -d lm # Unpacks to "lm". unzip lm_train_pbr.zip -d lm # Unpacks to "lm".
15 texture-less household objects with discriminative color, shape and size. Each object is associated with a test image set showing one annotated object instance with significant clutter but only mild occlusion.
Provides additional ground-truth annotations for all modeled objects in one of the test sets from LM. This introduces challenging test cases with various levels of occlusion. Note the PBR-BlenderProc4BOP training images are the same as for LM.
30 industry-relevant objects with no significant texture or discriminative color. The objects exhibit symmetries and mutual similarities in shape and/or size, and a few objects are a composition of other objects. Test images originate from 20 scenes with varying complexity. Only images from Primesense Carmine 1.09 are included in the archives below. Images from Microsoft Kinect 2 and Canon IXUS 950 IS are available at the project website. However, only the Primesense images can be used in the BOP Challenge 2019/2020.
28 objects captured in realistic industrial setups with a high-quality Gray-D sensor. The ground-truth 6D poses are publicly available only for the validation images, not for the test images.
33 objects (17 toy, 8 household and 8 industry-relevant objects) captured in 13 scenes with varying complexity. The ground-truth 6D poses are publicly available only for the validation images, not for the test images. The dataset includes images from Primesense Carmine 1.09 and Microsoft Kinect 2. Note that only the Primesense images can be used in the BOP Challenge 2019/2020.
28 toy grocery objects are captured in 50 scenes from 10 household/office environments. Up to 5 lighting variations are captured for each scene, including backlighting and angled direct lighting with cast shadows. Scenes are cluttered with varying levels of occlusion. The collection of toy objects is available from online retailers for about 50 USD (see "dataset_info.md" in the base archive for details).
The 80K synthetic training images included in the original version of the dataset are also provided.
Rennie et al.: A dataset for improved RGBD-based object detection and pose estimation for warehouse pick-and-place, Robotics and Automation Letters 2016, project website.
14 textured products from the Amazon Picking Challenge 2015 , each associated with test images of a cluttered warehouse shelf.
Doumanoglou et al.: Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd, CVPR 2016, project website.
Test images of two objects from IC-MI, which appear in multiple locations with heavy occlusion in a bin-picking scenario.
Tejani et al.: Latent-class hough forests for 3D object detection and pose estimation, ECCV 2014, project website.
Two texture-less and four textured household objects. The test images show multiple object instances with clutter and slight occlusion.
Hodan, Michel et al.: BOP: Benchmark for 6D Object Pose Estimation, ECCV 2018, license: CC BY-SA 4.0.
Training and test image sequences show three moving objects under eight lighting conditions.
Hodan, Michel et al.: BOP: Benchmark for 6D Object Pose Estimation, ECCV 2018, license: CC BY-NC 4.0.
21 objects, each captured in multiple poses on a table-top setup, with four different table cloths and five different lighting conditions.
The thumbnails of the datasets were obtained by rendering colored 3D object models in the ground truth 6D poses over darkened test images.