@nv-nguyen
　Hi, thanks for sharing so nice work. I have some questions to understand your paper.

1. Could you mind offering more experiment details on YCB-Video dataset if you have done experiments on this dataset?
2. How to choose the right one rotation prediction from (len_sequences - 1) predictions, and prediction code is here?

Hi,

I loved reading the paper and was wondering when the source code would be uploaded.

Welcome update to OpenMMLab 2.0

I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial Intelligence Conference in Shanghai. We invite you to upgrade your algorithm library to OpenMMLab 2.0 using MMEngine, which can be used for both research and commercial purposes. If you have any questions, please feel free to join us on the OpenMMLab Discord at https://discord.gg/amFNsyUBvm or add me on WeChat (van-sin) and I will invite you to the OpenMMLab WeChat group.

Here are the OpenMMLab 2.0 repos branches:

Attention: please create a new virtual environment for OpenMMLab 2.0.

Hello, though feeling very impressive to read such excellent work, I have a question about how to evaluate the metrics like ADD(S), K° Kcm, proj2d. I mean, you estimate the relative transformation between the consecutive frames, so the result could be worse and worse with a long term tracking because of the accumulation of errors. So when evaluating the results, are there any methods to re-localization the object or just use the ground-truth pose regularly? If the result comes with no re-localization procedure. How long can this pipeline track? Thanks.

What package is needed in Ubuntu 22.04 for this?

(pizza) mona@ard-gpu-01:~/pizza$ bash ./scripts/download_uvo_weights.sh 
./scripts/download_uvo_weights.sh: line 1: ddl: command not found
./scripts/download_uvo_weights.sh: line 2: ddl: command not found
./scripts/download_uvo_weights.sh: line 3: ddl: command not found