LCS: An AI-based Low-Complexity Scaler for Power-Efficient Super-Resolution of Game Content
This work addresses power efficiency for game developers and players by enabling upscaling on resource-constrained devices, but it is incremental as it builds on existing efficient super-resolution models.
The paper tackles the problem of high GPU workload in modern game rendering by proposing an AI-based low-complexity scaler (LCS) for super-resolution, which achieves better perceptual quality compared to existing hardware-based methods like AMD EASF and FSR1.
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.