shangbuhuan13/SO-Pose
This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation
PythonApache-2.0
Issues
- 1
Models link not working
#19 opened by Daniil-Osokin - 2
生成xyz_crop时碰到的一些问题
#18 opened by micki-37 - 2
LINEMOD results
#17 opened by dkoguciuk - 1
linemod results with resnet50 or resnet34
#16 opened by GUOShuxuan - 4
Some error questions about generate_P_fast.py
#13 opened by micki-37 - 3
缺失lib.egl_renderer
#14 opened by jiaming3 - 0
缺少lib.egl_renderer
#15 opened by lyj9494 - 3
请问在可视化结果时可以提供一下你们的lib.egl_renderer吗,感谢。
#9 opened by liuicheng123 - 0
Some questions about generate_pbr_P_fast.py
#12 opened by micki-37 - 6
- 8
- 2
How can I inference the results?
#8 opened by RoyAmoyal - 2
配置文件中`TRAIN2=("lmo_pbr_train")`是否必要
#7 opened by flyinghu123 - 1
How to evaluate the trained model on YCBV?
#6 opened by DecaYale - 1
对于real+syn实验的疑问
#5 opened by wangJK20191 - 7
没有egl_renderer
#2 opened by peppa114 - 1
关于configs/gdrn_selfocc/lm参数设置
#4 opened by JiayuLL - 2
请问在训练过程中,cpu无法跑满怎么办。
#3 opened by liuicheng123 - 3
Since we need ground truth 2D-3D matching and self-occlusion results, we provide generation methods in .gdrn_selfocc_modeling/tools. Please refer to generate_*.py.
#1 opened by YC0315