gaussian-grouping

gaussian-grouping copied to clipboard

Background Removal

2

Thanks for your brilliant work, I was trying to crop an object out of a scene and remove all its background. Is it able to do this? Thanks in advance

LaFeuilleMorte

CUDA out of memory

1

May I ask what kind of graphics card is needed to handle this method? My 4090 indicates insufficient VRAM.

wangfeng70117

Deva run out of memory with "Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use."

3

 Hello, when I try to find the dynamic masks of the video,my gpu memory was run out, how can i solve it? I used 4070 GPU. Thank you！

zhangzehao123

Can we obtain the each instance segmentation part ply file?

2

Can we obtain the each instance segmentation part ply file?

Lizhinwafu

how to view the scene after segmentation.

1


zero-joke

Thanks for your brilliant work first. In the official repo, there're no demos on how to editting the gaussians with text-prompts. (Only an object id for removal/inpainting tasks), However, this...

LaFeuilleMorte

Hi, thanks for this great work! I notice that the ground truth for "teatime" test image 1 is missing in the hugging face dataset. I wonder if you can fix...

weijielyu

About the pose of the evaluation to calculate IoU.

1

In the dataset you release, I can't see the pose of each test view.Could you tell me where the pose is? Thank you very much. | |____test_mask | |____ |...

jmchensc

Training and fine-tuning are too slow

11

To train the bear model (original loss + 2d id loss + 3d reg loss), it would cost at least 10h. To fine-tune the inpainted model, it would cost at...

ThePassedWind

Could you share the LERF-Mask dataset described in Figure 11 and appendix 6.2 of the paper?

2

Hi. Thank you for your great work. Could you share the LERF-Mask dataset described in Figure 11 and appendix 6.2 of the paper? I think it would help a lot....

seokhunchoi