Lightweight Image Super-Resolution with Information Multi-distillation Network (ACM MM 2019, Winner Award of ICCVW AIM 2019 Constrained SR Track1&Track2)

A generic framework which implements some famouts super-resolution models

Quickly process image super-resolution reconstruction at any scale ratio

First thermal super-resolution system to achieve 34.2 dB PSNR at 229+ FPS using novel IMDN architecture with specialized thermal adaptations. Features breakthrough RGB→thermal transfer learning, thermal-aware multi-component loss, and real-time inference (2x: 270.6 FPS, 3x: 256.1 FPS, 4x: 250.9 FPS). Production-ready PyTorch + CUDA implementation