LCS: An AI-based Low-Complexity Scaler for Power-Efficient Super-Resolution of Game Content

TL;DR

This paper introduces LCS, an AI-based low-complexity super-resolution scaler designed to reduce GPU workload in gaming by offloading to low-power devices, achieving better perceptual quality than existing methods.

Contribution

The paper presents a novel low-complexity ESR model trained with adversarial techniques, optimized for deployment on resource-constrained hardware, outperforming existing upscaling solutions.

Findings

LCS achieves superior perceptual quality compared to AMD's EASF and FSR1.

LCS reduces model complexity through reparameterization and quantization.

LCS effectively offloads GPU workload to low-power devices.

Abstract

The increasing complexity of content rendering in modern games has led to a problematic growth in the workload of the GPU. In this paper, we propose an AI-based low-complexity scaler (LCS) inspired by state-of-the-art efficient super-resolution (ESR) models which could offload the workload on the GPU to a low-power device such as a neural processing unit (NPU). The LCS is trained on GameIR image pairs natively rendered at low and high resolution. We utilize adversarial training to encourage reconstruction of perceptually important details, and apply reparameterization and quantization techniques to reduce model complexity and size. In our comparative analysis we evaluate the LCS alongside the publicly available AMD hardware-based Edge Adaptive Scaling Function (EASF) and AMD FidelityFX Super Resolution 1 (FSR1) on five different metrics, and find that the LCS achieves better perceptual quality, demonstrating the potential of ESR models for upscaling on resource-constrained devices.