Gaozihui

Hi~ thank you for your contribution on MVS community. I am training Pairnet on another dataset and I am not sure about the correctness of the results after the first...

Question about coordinate transformation in triangulation with known camera poses

2

Hello, I have a query about [triangulation with known camera poses](https://colmap.github.io/faq.html#reconstruct-sparse-dense-model-from-known-camera-poses). I use DTU official world matrix to get w2c matrix and succeed on sparse reconstrucion but i did not...

Confusing results for DTU dataset with known official pose

2

Hi, I use DTU official pose as known prior to get colmap results by [triangulation with known camera poses](https://colmap.github.io/faq.html#reconstruct-sparse-dense-model-from-known-camera-poses)and then put it into gs for rendering. However, I found the...

Any suggestion about fine-tuning on another outdoor dataset

5

Thanks for your brilliant work. I am trying to use the pre-trained model to fine-tune on another outdoor dataset. Should I use the pretrained model ZoeD_M12_K.pt or the pretrained model...

Details about input views

1

Hi, great work! I noticed that "input views are in (36, 72), other views are randomly selected" in provider_objaverse and your dataset contains 100 images every object. So, I want...

Problems when 3 input views

1

Thanks for your great work! I have two problems about 3 input views: 1. I test 2 views and 3 views respectively with json files: `{"41bcd011f99bfb66":{"context": [4, 50], "target": [7,...