Total runs:
1.8K
Run Growth:
1.6K
Growth Rate:
89.76%
Sponsored by
PoYo.AI
Arm / neural-super-sampling
Model's Last Updated: October 06 2026
image-to-image
Introduction of neural-super-sampling
Model Details of neural-super-sampling
Neural Super Sampling (NSS)
Neural Super Sampling (NSS) is an innovative, efficient network for temporal super sampling on mobile devices. Content rendered at 540p can be upscaled to 1080p, resulting in up to 50% GPU savings. With our retraining tools content creators and game studios can build derivatives of the model suited to artwork style and performance requirements.
🎥 Neural Super Sampling Demo
Model Details
Neural Super Sampling (NSS) is a parameter prediction model for real-time temporal super sampling developed by Arm, optimized for execution on Neural Accelerators (NX) in mobile GPUs. It enables high-resolution rendering at a lower compute cost by reconstructing high-quality output frames from low-resolution temporal inputs. NSS is particularly suited for mobile gaming, XR, and other power-constrained graphics use cases.
- Developed by: Arm Limited
- Model type: Temporal image super sampling
- License: Other
- Repository: Neural Graphics Model Gym
- Blog: How Neural Super Sampling Works
- Paper: Mobile Neural Super Sampling
- Quickstart with ML extensions for Vulkan® : ML extensions for Vulkan® Quickstart Guide
- Quickstart with Unreal : Neural Super Sampling Quickstart Guide for NSS integration into Unreal Engine
NSS is under active development with regular updates planned. As we increase the size and diversity of the training dataset we expect to see significant quality improvements. Follow Arm to stay up to date on the latest releases.
The model is released under Arm's AI Model Community License which allows NSS to be retrained on datasets captured from your own content. Future releases of the Neural Graphics Model Gym will provide the tools to capture and convert content for use in (re)retraining..
Uses
NSS can be directly integrated into graphics pipelines using ML extensions for Vulkan®. See included ML SDK for Vulkan scenario for the simplest way to evaluate the model. The scenario includes the necessary pre- and post-processing compute shaders along with a single frame worth of input data.
The recommended way of integrating the model into a graphics pipeline is by using the VGF Library from the ML SDK for Vulkan.
NSS is released under a permissive license designed to foster innovation in the graphics industry and provide differentiation to content creators.
Direct Use
NSS has been integrated into Unreal Engine via two plugins, the NSS Plugin for Unreal Engine and Unreal NNE Plugin for ML extensions for Vulkan . See our quick start guide for step-by-step instructions on how to use NSS in Unreal® Engine.
Out-of-Scope Use
- Not suited for non-temporal tasks such as a standalone image upsampling
Bias, Risks, and Limitations
- Requires accurate motion vectors and frame history for stable output
- May underperform in extremely low framerate scenarios (<10 FPS) with fast camera movement
- Padding of the input is needed if input dimensions are not divisible by 8
Recommendations
For ultra-low-FPS use cases, reduce the camera speed, acceleration, or both so that the relative motion between frames mimics the application running at a higher frame rate.
How to Get Started with the Model
This repository contains pre-trained weights and compiled NSS model in VGF format ready for integration with Vulkan applications.
The included Scenario demonstrates full execution of the model on a Vulkan compute-capable system. An Emulation Layer is provided to implement ML Extensions for Vulkan where it is not supported by the native Vulkan driver.
Download and Prepare the Scenario
Clone the NSS model repository from Hugging Face
git clone https://huggingface.co/Arm/neural-super-sampling
cd neural-super-sampling
Run the Scenario
The NSS Hugging Face repository includes pre-built Windows® binaries for ML Emulation Layer for Vulkan and Scenario Runner. For other platforms,
- build from source following the instructions for Building the Emulation Layer from source and Building the Scenario Runner from source
- adapt the instructions below accordingly
-
Set the required environment variables:
On Windows:
$env:VK_LAYER_PATH="$PWD\bin\windows-x86_64" $env:VK_INSTANCE_LAYERS="VK_LAYER_ML_Graph_Emulation;VK_LAYER_ML_Tensor_Emulation"On Linux (assuming the Emulation Layer binaries and JSON files and Scenario Runner executable are copied to
bin/linux-x86_64):export LD_LIBRARY_PATH=$PWD/bin/linux-x86_64:$LD_LIBRARY_PATH export VK_LAYER_PATH=$PWD/bin/linux-x86_64 export VK_INSTANCE_LAYERS=VK_LAYER_ML_Graph_Emulation:VK_LAYER_ML_Tensor_Emulation -
Execute the scenario:
On Windows:
bin\windows-x86_64\scenario-runner.exe --scenario scenario\scenario.json --output outOn Linux:
bin/linux-x86_64/scenario-runner --scenario scenario/scenario.json --output out
-
Output images are encoded as
B10G11R11_UFLOAT. This format is common for framebuffers but not widely supported by image viewers. Use RenderDoc to view these images.
Training and Evaluation
For background on NSS architecture and training read our blog: How Neural Super Sampling Works
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
- Examples and tutorials: https://github.com/arm/neural-graphics-model-gym-examples
- Sample dataset: https://huggingface.co/datasets/Arm/neural-graphics-dataset
🔎 Model Explorer VGF extension
The VGF extension to Model Explorer provides a simple interface to visualize model and analyse VGF composition.
License
- The license for the model source code can be found here .
- The license for the content of this repository can be found here
More Information
🧑🔬 More technical details about the model can be found in the NSS Guide .
👩🏽💻 Our Neural Graphics Development Kit contains engine plugins, model training tools, code examples and extensive developer documentation.
🙋🏻♀️ For questions or feedback please start a discussion
Trademark notice
Arm® is a registered trademarks of Arm Limited (or its subsidiaries) in the US and/or elsewhere.
Windows® is a trademark of the Microsoft group of companies.
Vulkan® is a registered trademark of the Khronos® Group .
Runs of Arm neural-super-sampling on huggingface.co
500
Total runs
13
24-hour runs
9
3-day runs
33
7-day runs
83
30-day runs
More Information About neural-super-sampling huggingface.co Model
Url of neural-super-sampling
neural-super-sampling huggingface.co Url
Provider of neural-super-sampling huggingface.co
Other API from Arm
Updated:September 07 2026
Total runs:
1.2K
Run Growth:
1.1K
Growth Rate:
74.36%
Total runs:
824
Run Growth:
-133
Growth Rate:
-16.14%
Total runs:
741
Run Growth:
605
Growth Rate:
81.65%
Total runs:
725
Run Growth:
725
Growth Rate:
100.00%
Total runs:
718
Run Growth:
718
Growth Rate:
100.00%
Total runs:
688
Run Growth:
537
Growth Rate:
78.05%
Total runs:
675
Run Growth:
656
Growth Rate:
96.76%
Total runs:
599
Run Growth:
501
Growth Rate:
83.64%
Total runs:
566
Run Growth:
511
Growth Rate:
78.25%
Total runs:
497
Run Growth:
386
Growth Rate:
77.67%
Total runs:
491
Run Growth:
450
Growth Rate:
91.65%
Total runs:
464
Run Growth:
447
Growth Rate:
100.00%
Total runs:
438
Run Growth:
377
Growth Rate:
86.07%
Total runs:
385
Run Growth:
-8
Growth Rate:
-2.08%
Total runs:
374
Run Growth:
159
Growth Rate:
42.51%
Total runs:
350
Run Growth:
270
Growth Rate:
77.14%
Total runs:
332
Run Growth:
219
Growth Rate:
65.96%
Total runs:
287
Run Growth:
255
Growth Rate:
88.85%
Total runs:
256
Run Growth:
224
Growth Rate:
87.50%
Total runs:
232
Run Growth:
230
Growth Rate:
99.14%
Total runs:
219
Run Growth:
144
Growth Rate:
65.75%
Total runs:
209
Run Growth:
143
Growth Rate:
68.42%
Total runs:
173
Run Growth:
162
Growth Rate:
93.64%
Total runs:
158
Run Growth:
127
Growth Rate:
80.38%
Total runs:
148
Run Growth:
133
Growth Rate:
89.86%
Total runs:
133
Run Growth:
127
Growth Rate:
98.45%
Total runs:
132
Run Growth:
78
Growth Rate:
59.09%
Total runs:
130
Run Growth:
115
Growth Rate:
88.46%
Total runs:
123
Run Growth:
120
Growth Rate:
97.56%
Total runs:
117
Run Growth:
76
Growth Rate:
64.96%
Total runs:
111
Run Growth:
108
Growth Rate:
97.30%
Total runs:
108
Run Growth:
87
Growth Rate:
80.56%
Total runs:
105
Run Growth:
101
Growth Rate:
96.19%
Total runs:
99
Run Growth:
83
Growth Rate:
83.84%
Total runs:
91
Run Growth:
71
Growth Rate:
78.02%
Total runs:
90
Run Growth:
86
Growth Rate:
95.56%
Total runs:
88
Run Growth:
52
Growth Rate:
59.09%
Total runs:
88
Run Growth:
82
Growth Rate:
93.18%
Total runs:
73
Run Growth:
0
Growth Rate:
0.00%
Total runs:
72
Run Growth:
20
Growth Rate:
27.78%
Total runs:
68
Run Growth:
56
Growth Rate:
82.35%
Total runs:
65
Run Growth:
64
Growth Rate:
98.46%
Total runs:
62
Run Growth:
41
Growth Rate:
70.69%
Total runs:
50
Run Growth:
44
Growth Rate:
88.00%
Total runs:
49
Run Growth:
26
Growth Rate:
53.06%
Total runs:
48
Run Growth:
21
Growth Rate:
43.75%
Total runs:
48
Run Growth:
45
Growth Rate:
93.75%
Total runs:
46
Run Growth:
18
Growth Rate:
39.13%
Total runs:
43
Run Growth:
22
Growth Rate:
51.16%
Total runs:
40
Run Growth:
12
Growth Rate:
32.43%
Total runs:
39
Run Growth:
30
Growth Rate:
76.92%
Total runs:
34
Run Growth:
14
Growth Rate:
41.18%
Total runs:
33
Run Growth:
15
Growth Rate:
41.67%
Total runs:
16
Run Growth:
14
Growth Rate:
87.50%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%