BiohazardVFX/4DGaussians
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add-sibr-viewer-guidance

Browse Source
This commit is contained in:
guanjunwu 2024-02-28 21:19:31 +08:00
parent 535912c17b
commit 4a9d7517fa
6 changed files with 42 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -25,8 +25,8 @@ Light Gaussian implementation: [This link](https://github.com/pablodawson/4DGaus
## News
2024.02: Accepted by CVPR 2024. We delete some logging settings for debugging, the corrected training time is only **8 mins** (20 mins before) in D-NeRF datasets and **30 mins** (1 hour before) in HyperNeRF datasets. The rendering quality is not affected.
2024.02.28: Update SIBR viewer guidance.
2024.02.27: Accepted by CVPR 2024. We delete some logging settings for debugging, the corrected training time is only **8 mins** (20 mins before) in D-NeRF datasets and **30 mins** (1 hour before) in HyperNeRF datasets. The rendering quality is not affected.
## Environmental Setups
@ -133,7 +133,8 @@ cp -r data/your-ns-data/images data/your-ns-data/colmap/images
python train.py -s data/your-ns-data/colmap --port 6017 --expname "custom" --configs arguments/hypernerf/default.py
```
## Viewer
[Watch me](./docs/viewer_usage.md)
## Scripts
There are some helpful scripts in , please feel free to use them.

BIN
assets/port_forward.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 352 KiB

BIN
assets/viewer.mp4 Normal file
View File

Binary file not shown.

35
docs/viewer_usage.md Normal file
View File

@ -0,0 +1,35 @@
# 4D Gaussian Splatting
The viewer is downloads from [3D-GS](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/binaries/viewers.zip), you can extract the zip file under the folder of 4D-GS like:
```
├── 4DGaussians
| |viewers
| ├── bin
| ├── resources
| ├── shaders
| |...
| | train.py
| | test.py
| | ...(other files)
```
## How to use viewer?
If you train the 4D-GS on locally:
```python
./viewers/bin/SIBR_remoteGaussian_app.exe --port 6017 # port should be same with your trainging code.
```
If you train the 4D-GS on the server, you should add a port forward, in VSCode, like this:
![port_forward](../assets/port_forward.png)
Then you could clone this repo on your personal computer, and download a D-NeRF dataset, like this:
```
├── 4DGaussians
| |viewers
| ├── bin
| ├── resources
| ├── shaders
| |...
│ | data
│ ├── dnerf
| | train.py
| | test.py
| | ...(other files)
```
And the rendering speed may mainly depends on your network bandwidth.

2
submodules/depth-diff-gaussian-rasterization

@ -1 +1 @@
Subproject commit f2d8fa9921ea9a6cb9ac1c33a34ebd1b11510657
Subproject commit e49506654e8e11ed8a62d22bcb693e943fdecacf

4
train.py
View File

@ -403,8 +403,8 @@ if __name__ == "__main__":
parser.add_argument('--port', type=int, default=6009)
parser.add_argument('--debug_from', type=int, default=-1)
parser.add_argument('--detect_anomaly', action='store_true', default=False)
parser.add_argument("--test_iterations", nargs="+", type=int, default=[3000,14000,20000])
parser.add_argument("--save_iterations", nargs="+", type=int, default=[3000,14000,20000, 30_000, 45000, 60000])
parser.add_argument("--test_iterations", nargs="+", type=int, default=[3000,7000,14000])
parser.add_argument("--save_iterations", nargs="+", type=int, default=[ 14000, 20000, 30_000, 45000, 60000])
parser.add_argument("--quiet", action="store_true")
parser.add_argument("--checkpoint_iterations", nargs="+", type=int, default=[])
parser.add_argument("--start_checkpoint", type=str, default = None)