Submission: HccePose (FCOS)/TUD-L

Download submission
Submission name
Submission time (UTC) Oct. 22, 2023, 4:07 a.m.
User SEU_WYL
Task Model-based 6D localization of seen objects
Dataset TUD-L
Description
Evaluation scores
AR:0.862
AR_MSPD:0.979
AR_MSSD:0.855
AR_VSD:0.752
average_time_per_image:-1.000

Method: HccePose (FCOS)

User SEU_WYL
Publication
Implementation
Training image modalities RGB
Test image modalities RGB
Description

Submitted to: BOP Challenge 2023

Training data: real + provided PBR

Training Datasets of LM-O are real and PBR-based datasets.

Used 3D models: default

Notes:

Setting: One network (ResNet34) per object was trained (without Refinement)

2D Bounding Box: FCOS (ZebraPose)

Batch Size: 24

Epoch: 38k

Learning Rate: 0.0002

Computer specifications