Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update README.md #14

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update README.md #14

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,9 +20,10 @@ pip install -r requirements.txt
```

## Dataset
In our paper, we use the same dataset as in NeRF:
- [Blender](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1)
In our paper, we use the same dataset as in NeRF.
We only use LLFF dataset, but Blender is still possible:
- [LLFF](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1)
- [Blender](https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1)

However, our method is compatible to any dataset than can be trained on NeRF to perform super-resolution. Feel free to try out.

Expand Down Expand Up @@ -50,7 +51,7 @@ Please check the configuration in the scripts. You can always modify it to your
```bash
bash scripts/train_llff_downX.sh
```
to train a 504x378 NeRF with 252x179 inputs.
to train a 504x378 NeRF inputs.
or
```bash
bash scripts/train_blender_downX.sh
Expand All @@ -63,7 +64,8 @@ python warp.py
```
to create `*.loc` files. An example of `*.loc` files can be found in the provided `fern` checkpoints (in the `30_val_vis` folder), which can be used directly for refinement.

After that, you can train the refinement model:
After that, you can train the refinement model.
It is needed only for LLFF dataset:
```bash
bash scripts/train_llff_refine.sh
```
Expand Down