DOGS

DOGS copied to clipboard

About code

3

Great work! I want to know do you have a plan to release the code? I’m eager to give it a try.

cuijh26

A small spelling issue in paper

1


Beastmaster

Code Release

1

Hi, wonderful work done by you guys. Just wanted to ask when will you release the public code. Thanks

kunalkathare

The inconsistency between the paper description and the checkpoint

1

In your paper, you mentioned the validation setup: "_During training and evaluation, we adopt the original image splitting in Mega-NeRF and downsample the images by 6+ times from the original...

wangm-buaa

Thank you for your nice work. @AIBluefisher I would like to extract the point cloud from the pre-trained model _model.pth_ you provided. However, I found that the extracted scale is...

azhuantou

Thanks for your excellent work. Can I train a large scene in several chunks on a single GPU?

jayjungit

rows = db.execute("SELECT * FROM images") Can you provide pre-processed dataset? please！

2

It's a wonderful and amazing job! Thank you for sharing the code. However, when pre-processing the data, I find that in DOGS\scripts\preprocess\meganerf_to_colmap.py line 126 "database_path = os.path.join(scene_dir, 'database.db')" , the...

ori63174

Custom Large-Scale Dataset training with ADMM

4

Thank you very much for your excellent work and the released code! I have several questions about training on large-scale custom dataset (I've highlighted them in bold). I tried to...

yur1xfd

Some questions about the datasets arrangement

1

Hello, very impressed by your work! I've tried some work about large scale reconstruction built on 3dgs before, and I've tried to make the datasets of rubble, building, matrixcity and...

SwaggyM

bounding box issue

6

Thanks for your amazing job, I love this project the way I love you. 【I finished installing conda environment and tried training mipnerf360 dataset, then a error occured:】 Initialize 3DGS...

WWaynee