readme_updatae

README.md

@@ -16,6 +16,13 @@ Neural Frame Rate Upscaling (NFRU) is an efficient network for frame rate upscal
 
 With our [retraining tools](https://github.com/arm/neural-graphics-model-gym) content creators and game studios can build derivatives of the model suited to artwork style and performance requirements.
 
+## 🎥 Neural Frame Rate Upscaling Demo
+
+<video controls width="100%">
+  <source src="https://huggingface.co/Arm/neural-frame-rate-upscaling/resolve/main/resources/NFRU_Launch_Demo.mp4" type="video/mp4">
+  Your browser does not support the video tag.
+</video>
+
 ## Model Details
 Neural Frame Rate Upscaling (NFRU) is a model that predicts the correct parameters needed to generate _Frame T_ using information from _Frame T-1_ and _Frame T+1_. The model, developed by Arm, is optimized for execution on Neural Accelerators (NX) in mobile GPUs. NFRU is particularly suited for mobile gaming, XR, and other power-constrained graphics use cases.
 
@@ -122,6 +129,8 @@ Output images are encoded as `B10G11R11_UFLOAT`. This format is common for frame
 
 ## Training and Evaluation
 
+For background on NFRU architecture and training please watch our [walkthrough presentation](https://www.youtube.com/watch?v=J-kcCPSOWXY).
+
 Training and evaluation details, including model architecture code, training pipeline, and test configurations, are available at:
 
 - Model training code: <https://github.com/arm/neural-graphics-model-gym>

resources/NFRU_Launch_Demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c28c94f7fa15f883dfb5b911189d4f8c1e6b23f4d44fd93d347b160fb8fe204
+size 395337624