Jianxin Huang

The paper has introduced the MRG method but I can not find someone who implements it, Do you have to test this method?

Hi, Have Kimera-VIO-ROS the tools to visualize the Delaunay Triangle result in the source image as readme?

Thanks for your release. I use this repo to replicate the FSM result, but it can not replicate it at all, RMSE is more than 170 without gt scale. Have...

a bug for load tiny DDAD

1

Thanks for your code, it's great works! I use [this](https://github.com/TRI-ML/packnet-sfm/blob/6e3161f60e7161115813574557761edaffb1b6d1/packnet_sfm/datasets/dgp_dataset.py#L58 ) load the tiny dataset, but which have an assert error on [here](https://github.com/TRI-ML/dgp/blob/37eeab461419abd2bbef4bc42284eb2189c7643e/dgp/datasets/base_dataset.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L373 ), I found that the `datum_key_to_idx_in_scene` have...

Dreambooth微调问题

1

感谢开源！关于dreambooth微调问题，中文里如果选择触发词（就是论文里那个[V]）呢？用中文微调dreambooth效果都很差。

A question about the data augmentation

1

Great work and thanks for the code. The croco v2 carefully curated the dataset, I am curious about whether you have tried some strong data augmentation like dinov2? and I...

I observed a difference between my GPT-5 evaluation results on the ERQA dataset and the ones reported.

1

Thank you for your work! I have a question regarding the GPT-5 evaluation on the ERQA dataset in the latest InternVL3.5 paper. The reported GPT-5 score is 65.7, which seems...