Submission: SingleMultiPathEncoder-CVPR20/YCB-V

Download submission
Submission name
Submission time (UTC) Aug. 18, 2020, 2:11 p.m.
User MartinSmeyer
Task 6D localization of seen objects
Dataset YCB-V
Training model type Default
Training image type Synthetic + real
Description
Evaluation scores
AR:0.289
AR_MSPD:0.292
AR_MSSD:0.297
AR_VSD:0.279
average_time_per_image:0.181

Method: SingleMultiPathEncoder-CVPR20

User MartinSmeyer
Publication https://openaccess.thecvf.com/content_CVPR_2020/html/Sundermeyer_Multi-Path_Learning_for_Object_Pose_Estimation_Across_Domains_CVPR_2020_paper.html
Implementation https://github.com/DLR-RM/AugmentedAutoencoder/tree/multipath
Training image modalities RGB
Test image modalities RGB
Description

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