# Deep Adaptive Inference Networks for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/2004.03915 · HTML: https://mlsanity.com/paper/2004.03915/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 15 of 15)

- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution](https://mlsanity.com/paper/2207.10345/) (2022)
- [AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring](https://mlsanity.com/paper/2406.09135/) (2024)
- [Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations](https://mlsanity.com/paper/2203.01325/) (2022)
- [Adaptive Patch Exiting for Scalable Single Image Super-Resolution](https://mlsanity.com/paper/2203.11589/) (2022)
- [NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results](https://mlsanity.com/paper/2505.12089/) (2025)
- [Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity](https://mlsanity.com/paper/2309.06626/) (2023)
- [AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution](https://mlsanity.com/paper/2404.03296/) (2024)
- [Accelerating Image Super-Resolution Networks with Pixel-Level Classification](https://mlsanity.com/paper/2407.21448/) (2024)
- [AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution](https://mlsanity.com/paper/2410.17752/) (2024)
- [A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution](https://mlsanity.com/paper/2210.08229/) (2022)
- [RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution](https://mlsanity.com/paper/2306.17595/) (2023)
- [GRAN: Ghost Residual Attention Network for Single Image Super Resolution](https://mlsanity.com/paper/2302.14557/) (2023)
- [Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations](https://mlsanity.com/paper/2405.02171/) (2024)
- [High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution](https://mlsanity.com/paper/2505.06975/) (2025)

## Abstract (arXiv)

Recent years have witnessed tremendous progress in single image super-resolution (SISR) owing to the deployment of deep convolutional neural networks (CNNs). For most existing methods, the computational cost of each SISR model is irrelevant to local image content, hardware platform and application scenario. Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints. In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR). In particular, our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth. Adaptive inference can then be performed with the support of efficient sparse convolution, where only a fraction of the layers in the backbone is performed at a given position according to its predicted depth. The network learning can be formulated as the joint optimization of reconstruction and network depth losses. In the inference stage, the average depth can be flexibly tuned to meet a range of efficiency constraints. Experiments demonstrate the effectiveness and adaptability of our AdaDSR in contrast to its counterparts (e.g., EDSR and RCAN).