Different test results on TUM-VI datasets

[Dynamite321]

Hi,

I downloaded your pre-trained model on TUM-VI and evaluated it by the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation, which is also recommended by open-vins (https://docs.openvins.com/namespaceov__eval.html). The AOE results for rooms 2, 4, and 6 are 1.87, 1.44, and 1.93, respectively. However, the results provided by your paper are 1.31, 1.48, and 1.04. I wonder whether this is because of the existence of outliers in TUM-VI datasets and I need to remove them before I run the evaluation. Could you please give me any clue?

P.S. The evaluation results of EuRoC datasets with the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation are exactly the same as your paper.

Thanks!

[RXvo]

Hi,

I downloaded your pre-trained model on TUM-VI and evaluated it by the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation, which is also recommended by open-vins (https://docs.openvins.com/namespaceov__eval.html). The AOE results for rooms 2, 4, and 6 are 1.87, 1.44, and 1.93, respectively. However, the results provided by your paper are 1.31, 1.48, and 1.04. I wonder whether this is because of the existence of outliers in TUM-VI datasets and I need to remove them before I run the evaluation. Could you please give me any clue?

P.S. The evaluation results of EuRoC datasets with the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation are exactly the same as your paper.

Thanks!

你好 请问你还有这个程序的优化参数和对应的数据集吗 感谢

[successkaisadadi]

Hi,

I downloaded your pre-trained model on TUM-VI and evaluated it by the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation, which is also recommended by open-vins (https://docs.openvins.com/namespaceov__eval.html). The AOE results for rooms 2, 4, and 6 are 1.87, 1.44, and 1.93, respectively. However, the results provided by your paper are 1.31, 1.48, and 1.04. I wonder whether this is because of the existence of outliers in TUM-VI datasets and I need to remove them before I run the evaluation. Could you please give me any clue?

P.S. The evaluation results of EuRoC datasets with the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation are exactly the same as your paper.

Thanks!
Hello, has your problem been solved? You can try using the evaluation tool provided by openvins！

[huazai665]

This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation

[scarLiu]

This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation

你好！你的数据集和优化参数现在还在嘛，可否给我发一份？[email protected]

[dreamer1031]

This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation

你好！你的数据集和优化参数现在还在嘛，可否给我发一份？[email protected]

do you get the dataset and parameters now? if you do , can you send one to me ? my email address is [email protected]! thank you !

[alun9258]

Hi,
I downloaded your pre-trained model on TUM-VI and evaluated it by the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation, which is also recommended by open-vins (https://docs.openvins.com/namespaceov__eval.html). The AOE results for rooms 2, 4, and 6 are 1.87, 1.44, and 1.93, respectively. However, the results provided by your paper are 1.31, 1.48, and 1.04. I wonder whether this is because of the existence of outliers in TUM-VI datasets and I need to remove them before I run the evaluation. Could you please give me any clue?
P.S. The evaluation results of EuRoC datasets with the toolbox provided by https://github.com/uzh-rpg/rpg_trajectory_evaluation are exactly the same as your paper.
Thanks!

你好 请问你还有这个程序的优化参数和对应的数据集吗 感谢

Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！

[alun9258]

This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation

你好！你的数据集和优化参数现在还在嘛，可否给我发一份？[email protected]

Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！[email protected]

[alun9258]

This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation

你好！你的数据集和优化参数现在还在嘛，可否给我发一份？[email protected]

do you get the dataset and parameters now? if you do , can you send one to me ? my email address is [email protected]! thank you !

Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！[email protected]

[glunekoqu]

Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！[email protected]

This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation这是我根据 openVins 得出的结果，但我在结果中没有找到 AOE，结果与纸质中的 AOE 不同。我也在 https://github.com/uzh-rpg/rpg_trajectory_evaluation 中对其进行了测试这是我根据 openVins 得出的结果，但我在结果中没有找到 AOE，结果与纸质中的 AOE 不同。我也在 https://github.com/uzh-rpg/rpg_trajectory_evaluation 中对其进行了测试

Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！[email protected]

[BahMoh]

https://github.com/BahMoh/TUMVI-IMU-only-Dataset-room1-to-room6 https://github.com/BahMoh/denoise-imu-gyro

…

On Wed, 9 Oct 2024 at 07:51, glunekoqu ***@***.***> wrote: Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！ ***@***.*** [image: image] <https://user-images.githubusercontent.com/32571541/174520529-ad139058-84d3-48a1-b168-1e6089d55a61.png> This is my results according to openVins, but I don't find AOE in result, and the result is not same as the AOE in paper. I also test it in https://github.com/uzh-rpg/rpg_trajectory_evaluation这是我根据 openVins 得出的结果，但我在结果中没有找到 AOE，结果与纸质中的 AOE 不同。我也在 https://github.com/uzh-rpg/rpg_trajectory_evaluation 中对其进行了测试这是我根据 openVins 得出的结果，但我在结果中没有找到 AOE，结果与纸质中的 AOE 不同。我也在 https://github.com/uzh-rpg/rpg_trajectory_evaluation 中对其进行了测试 Hello, do you still have the corresponding optimization parameters and data set of this code? The author's links have all failed. Thank you！ ***@***.*** — Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AU5QSSO32Y6P4UVEQZ2YE7TZ2SVM7AVCNFSM6AAAAABPTTZJJ2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDIMBRGI4DIMBQGQ> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[TK72]

Hello, the url that providing the corresponding dataset is failed. Do you still store the datasets of this paper? If so, please send me one copy. My email address is [email protected]. Thank you!!