Skip to content
This repository was archived by the owner on Jul 18, 2025. It is now read-only.

Latest commit

 

History

History

README.md

SESR INT8

Description

SESR, super-efficient super resolution is a network aims to generate a high-resolution image from a low-resolution input. Name was changed by ARM developers when they wrote research paper on their technique. The attached int8 fully quantized tflite model achieves 35.00dB PSNR on DIV2K dataset. The model takes 1080p input (in YCbCr, i.e., takes a 1x1920x1080x1 tensor as input) and outputs 4K images (in YCbCr, i.e., 1x3840x2160x1 output).
Compatability note:
Please note that SESR is a high-end network operating on 1080p->4K images and runtime memory use of this network requires an end system with at least 100MB of memory available to ensure successful execution. We anticipate the network being used in premium devices as part of a camera imaging pipeline providing highest quality digital zoom.
Repository for model authors: https://github.com/ARM-software/sesr

License

Apache-2.0

Network Information

Network Information Value
Framework TensorFlow Lite
SHA-1 Hash 5abc5f05202aa1b0b9c34c5a978b6aa0a02f7ec5
Size (Bytes) 23680
Provenance https://arxiv.org/abs/2103.09404
Paper https://arxiv.org/abs/2103.09404

Performance

This model has a large memory footprint – it will not run on all platforms.

Platform Optimized
Cortex-A ✔️
Cortex-M ✖️
Mali GPU ✔️ HERO
Ethos U ✖️

Key

  • ✔️ - Will run on this platform.
  • ✖️ - Will not run on this platform.

Accuracy

Dataset: DIV2K

Metric Value
PSNR 35.00dB

Optimizations

Optimization Value
Quantization INT8

Network Inputs

Input Node Name Shape Description
net_input (1, 1920, 1080, 1) Low-resolution input: 1080p (in YCbCr, i.e., take a 1x1920x1080x1 tensor as input)

Network Outputs

Output Node Name Shape Description
net_output (1, 3840, 2160, 1) High-resolution input: 4K images (in YCbCr, i.e., 1x3840x2160x1 output).