Submission: DOPE/HOPE/DOPE-400

Download submission
Submission name DOPE-400
Submission time (UTC) Oct. 6, 2021, 5:16 p.m.
User swtyree
Task Model-based 6D localization of seen objects
Dataset HOPE
Training model type Default
Training image type Synthetic (custom)
Description
Evaluation scores
AR:0.357
AR_MSPD:0.498
AR_MSSD:0.297
AR_VSD:0.277
average_time_per_image:-1.000

Method: DOPE

User swtyree
Publication Tremblay, et al., "Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects", CoRL 2018.
Implementation https://github.com/NVlabs/Deep_Object_Pose
Training image modalities RGB
Test image modalities RGB
Description
Computer specifications