Yihao Wang

This is because the model downloaded by download.py is incomplete (you can check the *.pt file yourself). Downloading the complete file from the author's Google Drive and putting it in...

This is because the annotate is deprecated in higher versions on `supervision`: `BoxAnnotator` is deprecated and will be removed in `supervision-0.22.0`. Use `BoundingBoxAnnotator` and `LabelAnnotator` instead This issue can be...

By default, the evaluation dataset is the clean data. However, you can enable debug mode to render the dynamic part of the training (cluttered) dataset by using the ```--eval_train``` flag....

Hi! Thanks for your attention. I reran the script but didn’t encounter the bug on my end. Could you please provide a screenshot of the error when it occurs? How...

Hi! Thanks for your interest. This is indeed our limitation, which we have stated in our paper. This issue is because our method learns to distinguish distractor and static objects...

Hi! Thanks for your interest. Yes, we have a gsplat version with its core functionality, based on `gsplat/examples/simple_trainer.py`. There are a few differences in the training strategy (e.g., threshold and...

Hi! I have uploaded the gsplat version to this repo, please check [gsplat branch](https://github.com/AaltoML/desplat/tree/gsplat). The gsplat version is 1.0.0. There are some differences in the pipelines of newer versions, which...

In our ablation study, we ran with varying ratios of cluttered images. As the proportion of cluttered images increases, a slight performance drop is expected. However, our method maintains relative...