[ L_total = L_pixel + \lambda_1 L_perceptual + \lambda_2 L_adversarial + \lambda_3 L_edge ]
| Metric | Description | Optimized For | |--------|-------------|----------------| | (Peak Signal-to-Noise Ratio) | Pixel-level MSE in log scale | Fidelity (L2 optimization) | | SSIM (Structural Similarity) | Luminance, contrast, structure | Structural preservation | | LPIPS (Learned Perceptual Image Patch Similarity) | Deep feature distance | Perceptual similarity | | NIQE (Natural Image Quality Evaluator) | No-reference, blind | Real-world deployment | | FLOPS / Inference Time | Computational cost | Real-time applications | | Model Size (MB) | Memory footprint | Mobile/edge deployment | imgsrro
Super-resolution (SR) refers to the process of taking one or more low-resolution (LR) images and generating a high-resolution (HR) output. When "Optimization" is added, it emphasizes making these models efficient for real-world deployment, balancing trade-offs between accuracy, inference time, and computational cost. [ L_total = L_pixel + \lambda_1 L_perceptual +