mlsanityData to 7 Oct 2026

Dual-Camera Super-Resolution with Aligned Attention Modules

arXiv 2109.01349 ↗First posted 3 Sep 2021cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results. Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. We further explore the dual-camera super-resolution that is one promising application of RefSR, and build a dataset that consists of 146 image pairs from the main and telephoto cameras in a smartphone. To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy for real-world images. Extensive experiments on our dataset and a public benchmark demonstrate clear improvement achieved by our method over state of the art in both quantitative evaluation and visual comparisons.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 3 Sep 2021.

Builds on

28 of 47 references.

References · 28

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2017Deformable Convolutional Networkscited by 1,481
  6. 2015Spatial Transformer Networkscited by 1,423
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  10. 2017Deep Image Priorcited by 1,097
  11. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  12. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
16 more
  1. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  2. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  3. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  4. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  5. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  6. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  7. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  8. 2018The Contextual Loss for Image Transformation with Non-Aligned Datacited by 135
  9. 2020Contextual Residual Aggregation for Ultra High-Resolution Image Inpaintingcited by 124
  10. 2019Image Super-Resolution by Neural Texture Transfercited by 119
  11. 2019Zoom To Learn, Learn To Zoomcited by 114
  12. 2016Fast Patch-based Style Transfer of Arbitrary Stylecited by 92
  13. 2018CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warpingcited by 90
  14. 2020Understanding Deformable Alignment in Video Super-Resolutioncited by 78
  15. 2021Image Inpainting with External-internal Learning and Monochromic Bottleneckcited by 21
  16. 2018Maintaining Natural Image Statistics with the Contextual Losscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 10; 2024: 6; 2025: 6; 2026: 3.

33 papers.

Sort:

By area:

  1. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  2. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  3. 2022Bootstrap Motion Forecasting With Self-Consistent Constraintscited by 23
  4. 2022Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observationscited by 19
  5. 2022Reference-based Video Super-Resolution Using Multi-Camera Video Tripletscited by 19
  6. 2023Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Cameracited by 16
  7. 2022RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selectioncited by 12
  8. 2023LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolutioncited by 12
  9. 2023DC2: Dual-Camera Defocus Control by Learning to Refocuscited by 12
  10. 2022Reference-based Image and Video Super-Resolution via C2-Matchingcited by 8
  11. 2025C2PD: Continuity-Constrained Pixelwise Deformation for Guided Depth Super-Resolutioncited by 8
  12. 2025BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolutioncited by 6
21 more
  1. 2025Imaging for All-Day Wearable Smart Glassescited by 6
  2. 2022Degradation-agnostic Correspondence from Resolution-asymmetric Stereocited by 5
  3. 2023Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Paircited by 4
  4. 2023Toward Real-World Light Field Super-Resolutioncited by 3
  5. 2023RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolutioncited by 3
  6. 2023KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free Matchingcited by 3
  7. 2024Efficient Hybrid Zoom using Camera Fusion on Mobile Phonescited by 3
  8. 2022NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Camerascited by 2
  9. 2023Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Imagecited by 2
  10. 2024Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observationscited by 2
  11. 2024DeeDSR: Towards Real-World Image Super-Resolution via Degradation-Aware Stable Diffusioncited by 1
  12. 2024Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restorationcited by 1
  13. 2025UltraZoom: Generating Gigapixel Images from Regular Photoscited by 1
  14. 2023HSTR-Net: Reference Based Video Super-resolution with Dual Camerascited by 0
  15. 2024The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregationcited by 0
  16. 2024ReWiTe: Realistic Wide-angle and Telephoto Dual Camera Fusion Dataset via Beam Splitter Camera Rigcited by 0
  17. 2025DM3Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matchingcited by 0
  18. 2025Modulate and Reconstruct: Learning Hyperspectral Imaging from Misaligned Smartphone Viewscited by 0
  19. 2026BluRef: Unsupervised Image Deblurring with Dense-Matching Referencescited by 0
  20. 2026A Benchmark for Heterogeneous Stereo Deblurring with Physically- and Epipolar-constrained Cross Attentioncited by 0
  21. 2026Language-Assisted Super-Resolution from Real-World Low-Resolution Patchescited by 0