Method: SingleMultiPathEncoder-CVPR20

User MartinSmeyer
Training image modalities RGB
Test image modalities RGB

A single MultiPath Encoder model to predict the poses of all objects of all datasets in the BOP challenge (instead of training one model per object/dataset). Single object OpenGL renderings are used for training.

The single MultiPath Encoder achieves results similar to 108 separately trained AAE models used in the BOP19 challenge on pure RGB data. This result should serve as a baseline for learning-based pose-sensitive feature extraction that can scale to a large number of trained & untrained objects.

For instance segmentation we use dataset-wise trained MaskRCNNs (trained on BlenderProc PBR and real data).

Computer specifications Intel(R) Xeon(R) W-2133 CPU @ 3.60GHz + Intel Nvidia 1080 Ti

Public submissions

Date Submission name Dataset
2020-08-11 23:03 Test HB
2020-08-17 15:59 - LM-O
2020-08-18 09:44 - TUD-L
2020-08-18 11:23 - T-LESS
2020-08-18 14:11 - YCB-V
2020-08-18 16:15 - IC-BIN
2020-08-19 17:33 - ITODD