Kangle Deng
Kangle Deng
Thanks for your interest! 1. The camera's internal parameters are defined in the functions in this [file](https://github.com/dunbar12138/DSNeRF/blob/main/load_llff.py). 2. We uniformly sample the training sample from the LLFF dataset. 3. They...
Thanks for the pointer! It is fixed now.
Thanks for your interest! Please check [loss.py](https://github.com/dunbar12138/DSNeRF/blob/main/loss.py).
Thanks for your comments. We're developing a colab demo.
Thanks for your interest! You can find guidelines to run on your own data [here](https://github.com/dunbar12138/DSNeRF#how-to-run).
Thanks for your interest! We uniformly select the sparse views from the training set. Please check our dataset [here](https://drive.google.com/file/d/1RjhfcbsywOvw0ts1AFSri91mKANvEVOa/view?usp=sharing) for the specific image ids we select.
> I wrote some code to load the npy files, and but got a key error said: ``` shuffle rays i_train: [0 1] get depth rays Traceback (most recent call...
- We do not use extra images to obtain 3D points or camera poses. - Make sure you are running COLMAP on images of original resolution instead of downscaled ones....
We don't have the plan to submit it to any journals other than conferences right now.
Thanks for your interest! We will release the code and pretrained models for the redwood dataset soon.