# DRCT: Saving Image Super-resolution away from Information Bottleneck

arXiv: https://arxiv.org/abs/2404.00722 · HTML: https://mlsanity.com/paper/2404.00722/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 66 references that are in the map.
- First posted on arXiv 31 Mar 2024.

## Builds on (most cited first, 30 of 36)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [Understanding The Robustness in Vision Transformers](https://mlsanity.com/paper/2204.12451/) (2022)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://mlsanity.com/paper/2203.10981/) (2022)

## Built on by (most cited first, 30 of 40)

- [NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results](https://mlsanity.com/paper/2505.12089/) (2025)
- [CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference](https://mlsanity.com/paper/2501.15852/) (2025)
- [NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results](https://mlsanity.com/paper/2504.14582/) (2025)
- [PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation](https://mlsanity.com/paper/2411.15922/) (2024)
- [DenseSR: Image Shadow Removal as Dense Prediction](https://mlsanity.com/paper/2507.16472/) (2025)
- [Auto-Encoded Supervision for Perceptual Image Super-Resolution](https://mlsanity.com/paper/2412.00124/) (2024)
- [Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation](https://mlsanity.com/paper/2509.05746/) (2025)
- [NeurOp-Diff:Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion](https://mlsanity.com/paper/2501.09054/) (2025)
- [PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models](https://mlsanity.com/paper/2505.22394/) (2025)
- [Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization](https://mlsanity.com/paper/2507.19858/) (2025)
- [SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation](https://mlsanity.com/paper/2605.14847/) (2026)
- [Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures](https://mlsanity.com/paper/2404.06294/) (2024)
- [FIPER: Factorized Features for Robust Image Super-Resolution and Compression](https://mlsanity.com/paper/2410.18083/) (2024)
- [HyFusion: Enhanced Reception Field Transformer for Hyperspectral Image Fusion](https://mlsanity.com/paper/2501.04665/) (2025)
- [AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution](https://mlsanity.com/paper/2503.07748/) (2025)
- [AdaFortiTran: An Adaptive Transformer Model for Robust OFDM Channel Estimation](https://mlsanity.com/paper/2505.09076/) (2025)
- [CLIP-aware Domain-Adaptive Super-Resolution](https://mlsanity.com/paper/2505.12391/) (2025)
- [Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution](https://mlsanity.com/paper/2510.16752/) (2025)
- [INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts](https://mlsanity.com/paper/2511.22351/) (2025)
- [ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation](https://mlsanity.com/paper/2601.17468/) (2026)
- [Downscaling Neural Network for Coastal Simulations](https://mlsanity.com/paper/2408.16553/) (2024)
- [HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2411.18003/) (2024)
- [A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only](https://mlsanity.com/paper/2503.23265/) (2025)
- [DHECA-SuperGaze: Dual Head-Eye Cross-Attention and Super-Resolution for Unconstrained Gaze Estimation](https://mlsanity.com/paper/2505.08426/) (2025)
- [DiMoSR: Feature Modulation via Multi-Branch Dilated Convolutions for Efficient Image Super-Resolution](https://mlsanity.com/paper/2505.21262/) (2025)
- [STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution](https://mlsanity.com/paper/2506.16061/) (2025)
- [VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systems](https://mlsanity.com/paper/2507.05146/) (2025)
- [Fourier-Guided Attention Upsampling for Image Super-Resolution](https://mlsanity.com/paper/2508.10616/) (2025)
- [Pure-Pass: Fine-Grained, Adaptive Masking for Dynamic Token-Mixing Routing in Lightweight Image Super-Resolution](https://mlsanity.com/paper/2510.01997/) (2025)
- [2D Representation for Unguided Single-View 3D Super-Resolution in Real-Time](https://mlsanity.com/paper/2511.08224/) (2025)

## Abstract (arXiv)

In recent years, Vision Transformer-based approaches for low-level vision tasks have achieved widespread success. Unlike CNN-based models, Transformers are more adept at capturing long-range dependencies, enabling the reconstruction of images utilizing non-local information. In the domain of super-resolution, Swin-transformer-based models have become mainstream due to their capability of global spatial information modeling and their shifting-window attention mechanism that facilitates the interchange of information between different windows. Many researchers have enhanced model performance by expanding the receptive fields or designing meticulous networks, yielding commendable results. However, we observed that it is a general phenomenon for the feature map intensity to be abruptly suppressed to small values towards the network's end. This implies an information bottleneck and a diminishment of spatial information, implicitly limiting the model's potential. To address this, we propose the Dense-residual-connected Transformer (DRCT), aimed at mitigating the loss of spatial information and stabilizing the information flow through dense-residual connections between layers, thereby unleashing the model's potential and saving the model away from information bottleneck. Experiment results indicate that our approach surpasses state-of-the-art methods on benchmark datasets and performs commendably at the NTIRE-2024 Image Super-Resolution (x4) Challenge. Our source code is available at https://github.com/ming053l/DRCT