| schema_version: 1.0.0 |
| report_type: image-to-image |
| task_type: image-to-image |
| title: Neural Super Sampling (NSS) |
| description: >- |
| 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. |
| family_name: Neural Super Sampling |
| id: Arm/neural-super-sampling |
| filename: nss_v1_0_1_high_int8.vgf |
| base_model_id: Arm/neural-super-sampling |
| vendor: Arm |
| weight_dtype: int8 |
| profile: Arm-Optimized |
| related_technologies: |
| - NX |
| quantization: |
| method: QAT |
| weight_bits: 8 |
| activation_bits: 8 |
| model_size_mb: 0.16 |
| format: vgf |
|
|
