# PAMS: Quantized Super-Resolution via Parameterized Max Scale

arXiv: https://arxiv.org/abs/2011.04212 · HTML: https://mlsanity.com/paper/2011.04212/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 30 of 48)

- [FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation](https://mlsanity.com/paper/2303.17225/) (2023)
- [OMPQ: Orthogonal Mixed Precision Quantization](https://mlsanity.com/paper/2109.07865/) (2021)
- [NIPQ: Noise proxy-based Integrated Pseudo-Quantization](https://mlsanity.com/paper/2206.00820/) (2022)
- [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://mlsanity.com/paper/2105.10288/) (2021)
- [Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2112.08996/) (2021)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [Anchor-based Plain Net for Mobile Image Super-Resolution](https://mlsanity.com/paper/2105.09750/) (2021)
- [Towards Compact Single Image Super-Resolution via Contrastive Self-distillation](https://mlsanity.com/paper/2105.11683/) (2021)
- [Online Multi-Granularity Distillation for GAN Compression](https://mlsanity.com/paper/2108.06908/) (2021)
- [Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks](https://mlsanity.com/paper/2203.03844/) (2022)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [ARM: Any-Time Super-Resolution Method](https://mlsanity.com/paper/2203.10812/) (2022)
- [PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement](https://mlsanity.com/paper/2505.12266/) (2025)
- [CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large Input](https://mlsanity.com/paper/2304.06454/) (2023)
- [Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2307.08544/) (2023)
- [2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution](https://mlsanity.com/paper/2406.06649/) (2024)
- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables](https://mlsanity.com/paper/2303.14506/) (2023)
- [Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression](https://mlsanity.com/paper/2211.02854/) (2022)
- [Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2308.05022/) (2023)
- [Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions](https://mlsanity.com/paper/2106.03727/) (2021)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [RefQSR: Reference-based Quantization for Image Super-Resolution Networks](https://mlsanity.com/paper/2404.01690/) (2024)
- [Reciprocal Attention Mixing Transformer for Lightweight Image Restoration](https://mlsanity.com/paper/2305.11474/) (2023)
- [Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation](https://mlsanity.com/paper/2204.13873/) (2022)
- [Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks](https://mlsanity.com/paper/2307.13337/) (2023)
- [Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration](https://mlsanity.com/paper/2503.21970/) (2025)
- [Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution](https://mlsanity.com/paper/2404.02573/) (2024)
- [IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution](https://mlsanity.com/paper/2507.09923/) (2025)

## Abstract (arXiv)

Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited devices, which mainly arise from the floating-point storage and operations between weights and activations. Although previous endeavors mainly resort to fixed-point operations, quantizing both weights and activations with fixed coding lengths may cause significant performance drop, especially on low bits. Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop. To address these two issues, we propose a new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively. Finally, a structured knowledge transfer (SKT) loss is introduced to fine-tune the quantized network. Extensive experiments demonstrate that the proposed PAMS scheme can well compress and accelerate the existing SR models such as EDSR and RDN. Notably, 8-bit PAMS-EDSR improves PSNR on Set5 benchmark from 32.095dB to 32.124dB with 2.42× compression ratio, which achieves a new state-of-the-art.