Mingqiao Ye

Hi, if memory is not enough, you can try downsampling the resolution of your dataset.

Hi, you can refer to [this line](https://github.com/lkeab/gaussian-grouping/blob/main/edit_object_removal.py#L85) in object removal to use a similar function and save the instance part with a mask.

Hi, segmentation result visualization is implemented in [this function](https://github.com/lkeab/gaussian-grouping/blob/main/render.py#L95).

Hi, we will release the dataset this week, probably by Thursday.

Hi, we will organize all the checkpoints. But it may take some time because there are a lot of datasets and tasks. If you need checkpoints for some individual datasets,...

Hi, we update the [LERF-mask dataset](https://github.com/lkeab/gaussian-grouping/blob/main/docs/dataset.md) now and provide a script for calculating IoU and Boundary IoU metric in our paper. For checkpoints of these three datasets and rendering code...

Hi, we have updated the [checkpoints and segmentation code with text-prompt](https://github.com/lkeab/gaussian-grouping/blob/main/docs/dataset.md#2-render-mask-with-text-prompt) now. For the dataset question, yes we omit the annoations on those two views. Because I found these two...

Hi, this training time seems a bit strange. I have verified that our code of inpainting on the bear dataset with full resolution takes about 40 minutes. I use one...

> Hi, Thanks for open-sourcing your project! > > To add to this issue, I trained Gaussian Grouping on the lerf figurines dataset, and it took 1h20 (same scene on...

> Maybe it's my GPU problem, the GPU is too old. And I have another question about training and fine-tuning stages: It is obvious that as the training goes on,...