update

Author: Ruilong Li

README.md

@@ -0,0 +1,47 @@
+# Monoport
+
+## How to run Siggraph RTL Demo
+
+#### 0. Setup the repo
+```
+python setup.py develop
+```
+
+#### 1. Start the main process as a server. 
+```
+# if you want to use the input from a webcam:
+python RTL/main.py --use_server --ip <YOUR_IP_ADDRESS> --port 5555 --camera -- netG.ckpt_path ./data/PIFu/net_G netC.ckpt_path ./data/PIFu/net_C
+
+# or if you want to use the input from a image folder:
+python RTL/main.py --use_server --ip <YOUR_IP_ADDRESS> --port 5555 --image_folder <IMAGE_FOLDER> -- netG.ckpt_path ./data/PIFu/net_G netC.ckpt_path ./data/PIFu/net_C
+
+# or if you want to use the input from a video:
+python RTL/main.py --use_server --ip <YOUR_IP_ADDRESS> --port 5555 --videos <VIDEO_PATH> -- netG.ckpt_path ./data/PIFu/net_G netC.ckpt_path ./data/PIFu/net_C
+```
+
+If everything goes well, you should be able to see those logs after waiting for a few seconds:
+
+ loading networkG from ./data/PIFu/net_G ...
+ loading networkC from ./data/PIFu/net_C ...
+ initialize data streamer ...
+ Using cache found in /home/rui/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
+ Using cache found in /home/rui/.cache/torch/hub/NVIDIA_DeepLearningExamples_torchhub
+ * Serving Flask app "main" (lazy loading)
+ * Environment: production
+ WARNING: This is a development server. Do not use it in a production deployment.
+ Use a production WSGI server instead.
+ * Debug mode: on
+ * Running on http://<YOUR_IP_ADDRESS>:5555/ (Press CTRL+C to quit)
+
+#### 2. Access the server to start.
+Open the page `http://<YOUR_IP_ADDRESS>:5555/` on a web browser from any device (Desktop/IPad/IPhone), You should be able to see the **MonoPort VR Demo** page on that device, and at the same time you should be able to see the a screen poping up on your desktop, showing the reconstructed normal and texture image.
+
+#### 3. Play with VR demo. (TODO: bc of the https cert, this step is not easy for the public to use)
+As a VR prototype, this system also allow users to control the camera in the **MonoPort VR Demo** using the sensor from IPad/IPhone. To achieve that, you need to start another server :
+```
+python RTL/VRweb/server_webxr.py --port 8000 --cert ruilong
+```
+
+Then you can access `https://www/liruilong.codes:8000` from the app **XRViewer**, and click the button **Enter WebXR** in the page. From that moment, your mobile device would become a camera in our VR scene, and you can move your mobile device around to observe the reconstructed human.
+
+

RTL/main.py

@@ -64,6 +64,10 @@
  '--loop', action="store_true")
 parser.add_argument(
  '--use_server', action="store_true")
+parser.add_argument(
+ '--ip', type=str, default="192.168.1.53")
+parser.add_argument(
+ '--port', type=str, default="5555")
 
 argv = sys.argv[1:sys.argv.index('--')]
 args = parser.parse_args(argv)
@@ -186,7 +190,7 @@ def query_func(points, im_feat_list, calib_tensor):
  b_max=b_max.unsqueeze(0).numpy(),
  resolutions=resolutions,
  balance_value=0.5,
- use_cuda_impl=True,
+ use_cuda_impl=False,
  faster=True).to(cuda_recon)
 
 
@@ -602,7 +606,7 @@ def video_feed():
  mimetype = "multipart/x-mixed-replace; boundary=frame")
 
  # start the flask app
- app.run(host="192.168.1.53", port="5555", debug=True,
+ app.run(host=args.ip, port=args.port, debug=True,
  threaded=True, use_reloader=False)
  else:
  print('start main_loop.')