Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training

TL;DR

This paper introduces a deployment-aware quantized single-image super-resolution framework that balances quality, compactness, and robustness for low-bit mobile deployment, achieving high PSNR and SSIM scores.

Contribution

It proposes a three-stage training pipeline with teacher-guided supervision and quantization-aware training for efficient INT8 super-resolution models.

Findings

Achieved 29.79 dB PSNR and 0.8634 SSIM on the MAI 2026 challenge test set.

Teacher-guided supervision improves INT8 reconstruction quality.

Quantization stability is enhanced via weight clipping and BatchNorm recalibration.

Abstract

Efficient single-image super-resolution (SISR) requires balancing reconstruction fidelity, model compactness, and robustness under low-bit deployment, which is especially challenging for x3 SR. We present a deployment-oriented quantized SISR framework based on an extract-refine-upsample design. The student performs most computation in the low-resolution space and uses a lightweight re-parameterizable backbone with PixelShuffle reconstruction, yielding a compact inference graph. To improve quality without significantly increasing complexity, we adopt a three-stage training pipeline: Stage 1 learns a basic reconstruction mapping with spatial supervision; Stage 2 refines fidelity using Charbonnier loss, DCT-domain supervision, and confidence-weighted output-level distillation from a Mamba-based teacher; and Stage 3 applies quantization-aware training directly on the fused deploy graph. We further use weight clipping and BatchNorm recalibration to improve quantization stability. On the MAI 2026 Quantized 4K Image Super-Resolution Challenge test set, our final AIO MAI submission achieves 29.79 dB PSNR and 0.8634 SSIM, obtaining a final score of 1.8 under the target mobile INT8 deployment setting. Ablation on Stage 3 optimization shows that teacher-guided supervision improves the dynamic INT8 TFLite reconstruction from 29.91 dB/0.853 to 30.0003 dB/0.856, while the fixed-shape deployable INT8 TFLite artifact attains 30.006 dB/0.857.