Submission: HccePose(efficientnet-b4 & Default 2D BBOX)/T-LESS

Download submission
Submission name
Submission time (UTC) Feb. 29, 2024, 11:41 a.m.
User SEU_WYL
Task Model-based 6D localization of seen objects
Dataset T-LESS
Description
Evaluation scores
AR:0.843
AR_MSPD:0.948
AR_MSSD:0.814
AR_VSD:0.767
average_time_per_image:0.098

Method: HccePose(efficientnet-b4 & Default 2D BBOX)

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

Submitted to: BOP Challenge 2023

Training data: real + provided PBR

Used 3D models: default

Notes:

Setting: One network (EfficientNet b4) per object was trained (without Refinement)

2D Bounding Box: YOLOX (GDRNPP)

Batch Size: 12

Epoch: 60k

Learning Rate: 0.0002

GPU: RTX3080

CPU: E5-2680 v4 (7 vCPU)

Computer specifications