[misc] Add windows powershell scripts

.gitignore

@@ -20,3 +20,6 @@ data/*.MOV
 data/*.mp4
 data/colmap_text
 data/transforms.json
+lightning_logs
+*.zip
+external

README.md

@@ -42,6 +42,11 @@ To reach the best performance, here are the steps to follow:
 3. Uncomment `--half2_opt` to enable half2 optimization in the script, then `./scripts/train_nsvf_lego.sh`. For now, half2 optimization is only supported on Linux with Graphics Card Architecture >Pascal.
 
 
+**For Windows users**
+```
+./scripts/train_nsvf_lego.ps1
+```
+
 ### 360_v2 dataset
 
 Download [360 v2 dataset](http://storage.googleapis.com/gresearch/refraw360/360_v2.zip) and unzip it. Please keep the folder name unchanged. The default `batch_size=8192` takes up to 18GB RAM on a RTX3090. Please adjust `batch_size` according to your hardware spec. 
@@ -50,6 +55,12 @@ Download [360 v2 dataset](http://storage.googleapis.com/gresearch/refraw360/360_
 ./scripts/train_360_v2_garden.sh
 ```
 
+**For Windows users**
+```
+./scripts/train_360_v2_garden.ps1
+```
+
+
 ## Train with your own video
 
 Place your video in `data` folder and pass the video path to the script. There are several key parameters for producing a sound dataset for NeRF training. For a real scene, `scale`  is recommended to set to 16. `video_fps` determines the number of images generated from the video, typically 150~200 images are sufficient. For a one minute video, 2 is a suitable number. Running this script will preprocess your video and start training a NeRF out of it:
@@ -58,6 +69,13 @@ Place your video in `data` folder and pass the video path to the script. There a
 ./scripts/train_from_video.sh -v {your_video_name} -s {scale} -f {video_fps}
 ```
 
+**For Windows users**
+```
+./scripts/train_from_video.ps1
+```
+You need to download the colmap to extract the camera posture information. Download the colmap from [here](https://github.com/colmap/colmap/releases), and rename the directory to "colmap" and put it in the "external" directory under the project directory.  
+
+
 ## [Preview] Mobile Deployment
 
 Using [Taichi AOT](https://docs.taichi-lang.org/docs/tutorial), you can easily deploy a NeRF rendering pipeline on any mobile devices!

data/colmap2nerf.py

@@ -97,7 +97,7 @@ def run_colmap(args):
 
 	# On Windows, if FFmpeg isn't found, try automatically downloading it from the internet
 	if os.name == "nt" and os.system(f"where {colmap_binary} >nul 2>nul") != 0:
-		colmap_glob = os.path.join(ROOT_DIR, "external", "colmap", "*", "COLMAP.bat")
+		colmap_glob = os.path.join(ROOT_DIR, "external", "colmap", "COLMAP.bat")
 		candidates = glob(colmap_glob)
 		if not candidates:
 			print("COLMAP not found. Attempting to download COLMAP from the internet.")

scripts/train_360_v2_garden.ps1

@@ -0,0 +1 @@
+python train.py --root_dir ./360_v2/garden --dataset_name colmap --exp_name garden --downsample 0.25 --no_save_test --num_epochs 20 --scale 16.0 --gui

scripts/train_from_video.ps1

@@ -0,0 +1,20 @@
+#  Put your video in data/ folder and update filename VIDEO_FILE
+#  SCALE choose from 1, 4, 8, 16, 64; 16 is recommended for a real screne
+#  VIDEO_FPS = 2 is suitable for a one minute video 
+set VIDEO_FILE 'video.mp4' 
+set SCALE 16 
+set VIDEO_FPS 2 
+
+echo "video path $VIDEO_FILE"
+echo "scale $SCALE"
+echo "video fps $VIDEO_FPS"
+
+cd "data"
+
+python colmap2nerf.py --video_in $VIDEO_FILE --video_fps $VIDEO_FPS --run_colmap --aabb_scale $SCALE --images images
+
+Move-Item colmap_sparse sparse
+cd ..
+
+
+python train.py --root_dir data --dataset_name colmap --exp_name custom --downsample 0.25  --num_epochs 20 --scale $SCALE  --gui  

scripts/train_nsvf_lego.ps1

@@ -0,0 +1 @@
+python train.py --root_dir "./Synthetic_NeRF/Lego" --exp_name Lego --perf --num_epochs 20 --batch_size 8192 --lr 1e-2 --no_save_test --gui  --ckpt_path=./ckpts/nsvf/Lego/epoch=19-v2.ckpt --val_only