# AdderSR: Towards Energy Efficient Image Super-Resolution

arXiv: https://arxiv.org/abs/2009.08891 · HTML: https://mlsanity.com/paper/2009.08891/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2020.

## Built on by (most cited first, 30 of 32)

- [Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2203.14216/) (2022)
- [UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning](https://mlsanity.com/paper/2203.14542/) (2022)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Towards Compact Single Image Super-Resolution via Contrastive Self-distillation](https://mlsanity.com/paper/2105.11683/) (2021)
- [ARM: Any-Time Super-Resolution Method](https://mlsanity.com/paper/2203.10812/) (2022)
- [Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2307.08544/) (2023)
- [Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables](https://mlsanity.com/paper/2303.14506/) (2023)
- [DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables](https://mlsanity.com/paper/2503.15931/) (2025)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks](https://mlsanity.com/paper/2205.08119/) (2022)
- [In-Loop Filtering via Trained Look-Up Tables](https://mlsanity.com/paper/2407.10926/) (2024)
- [AdaDM: Enabling Normalization for Image Super-Resolution](https://mlsanity.com/paper/2111.13905/) (2021)
- [An Empirical Study of Adder Neural Networks for Object Detection](https://mlsanity.com/paper/2112.13608/) (2021)
- [Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution](https://mlsanity.com/paper/2312.06101/) (2023)
- [Winograd Algorithm for AdderNet](https://mlsanity.com/paper/2105.05530/) (2021)
- [Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution](https://mlsanity.com/paper/2404.02573/) (2024)
- [Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN](https://mlsanity.com/paper/2201.06383/) (2022)
- [DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution](https://mlsanity.com/paper/2212.07613/) (2022)
- [Deep Lookup Network](https://mlsanity.com/paper/2509.13662/) (2025)
- [ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation](https://mlsanity.com/paper/2407.02881/) (2024)
- [In-Loop Filtering Using Learned Look-Up Tables for Video Coding](https://mlsanity.com/paper/2509.09494/) (2025)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [GhostShiftAddNet: More Features from Energy-Efficient Operations](https://mlsanity.com/paper/2109.09495/) (2021)
- [A Novel Dual Dense Connection Network for Video Super-resolution](https://mlsanity.com/paper/2203.02723/) (2022)
- [Attention Mechanism with Energy-Friendly Operations](https://mlsanity.com/paper/2204.13353/) (2022)
- [DietCNN: Multiplication-free Inference for Quantized CNNs](https://mlsanity.com/paper/2305.05274/) (2023)
- [Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study](https://mlsanity.com/paper/2305.13232/) (2023)
- [A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution](https://mlsanity.com/paper/2309.13940/) (2023)
- [NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2409.16947/) (2024)

## Abstract (arXiv)

This paper studies the single image super-resolution problem using adder neural networks (AdderNet). Compared with convolutional neural networks, AdderNet utilizing additions to calculate the output features thus avoid massive energy consumptions of conventional multiplications. However, it is very hard to directly inherit the existing success of AdderNet on large-scale image classification to the image super-resolution task due to the different calculation paradigm. Specifically, the adder operation cannot easily learn the identity mapping, which is essential for image processing tasks. In addition, the functionality of high-pass filters cannot be ensured by AdderNet. To this end, we thoroughly analyze the relationship between an adder operation and the identity mapping and insert shortcuts to enhance the performance of SR models using adder networks. Then, we develop a learnable power activation for adjusting the feature distribution and refining details. Experiments conducted on several benchmark models and datasets demonstrate that, our image super-resolution models using AdderNet can achieve comparable performance and visual quality to that of their CNN baselines with an about 2× reduction on the energy consumption.