Submission: Sundermeyer-IJCV19+ICP/YCB-V

Download submission
Submission name
Submission time (UTC) Oct. 22, 2019, 9:09 a.m.
User MartinSmeyer
Task Model-based 6D localization of seen objects
Dataset YCB-V
Training model type Default
Training image type Real
Description Real data only used for instance segmentation
Evaluation scores
AR:0.505
AR_MSPD:0.475
AR_MSSD:0.581
AR_VSD:0.460
average_time_per_image:1.581

Method: Sundermeyer-IJCV19+ICP

User MartinSmeyer
Publication Sundermeyer et al.: Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection, ICJV 2019
Implementation https://github.com/DLR-RM/AugmentedAutoencoder
Training image modalities RGB
Test image modalities RGB-D
Description
Computer specifications Intel(R) Xeon(R) W-2133 CPU @ 3.60GHz + Intel Nvidia 1080 Ti