mlsanityData to 7 Oct 2026

BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow

arXiv 2409.15384 ↗First posted 21 Sep 2024eess.IV cs.CV cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Multi frame super-resolution(MFSR) achieves higher performance than single image super-resolution (SISR), because MFSR leverages abundant information from multiple frames. Recent MFSR approaches adapt the deformable convolution network (DCN) to align the frames. However, the existing MFSR suffers from misalignments between the reference and source frames due to the limitations of DCN, such as small receptive fields and the predefined number of kernels. From these problems, existing MFSR approaches struggle to represent high-frequency information. To this end, we propose Deep Burst Multi-scale SR using Fourier Space with Optical Flow (BurstM). The proposed method estimates the optical flow offset for accurate alignment and predicts the continuous Fourier coefficient of each frame for representing high-frequency textures. In addition, we have enhanced the network flexibility by supporting various super-resolution (SR) scale factors with the unimodel. We demonstrate that our method has the highest performance and flexibility than the existing MFSR methods. Our source code is available at https://github.com/Egkang-Luis/burstm

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 21 Sep 2024.

Builds on

32 of 46 references.

References · 32

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  7. 2017Deformable Convolutional Networkscited by 1,481
  8. 2018On the Spectral Bias of Neural Networkscited by 1,321
  9. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  10. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  11. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  12. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
20 more
  1. 2020Pre-Trained Image Processing Transformercited by 891
  2. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  3. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  4. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  5. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  6. 2020Local Implicit Grid Representations for 3D Scenescited by 372
  7. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  8. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  9. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  10. 2018Frame-Recurrent Video Super-Resolutioncited by 160
  11. 2021Local Texture Estimator for Implicit Representation Functioncited by 126
  12. 2021Deep Burst Super-Resolutioncited by 83
  13. 2021Burst Image Restoration and Enhancementcited by 64
  14. 2021Deep Reparametrization of Multi-Frame Super-Resolution and Denoisingcited by 39
  15. 2022BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignmentcited by 32
  16. 2023Burstormer: Burst Image Restoration and Enhancement Transformercited by 32
  17. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  18. 2022Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observationscited by 19
  19. 2023Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancementcited by 11
  20. 2023Implicit Neural Image Stitchingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  2. 2025Benchmarking Burst Super-Resolution for Polarization Images: Noise Dataset and Analysiscited by 3
  3. 2025Feature Alignment with Equivariant Convolutions for Burst Image Super-Resolutioncited by 0
  4. 2025Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decodingcited by 0
  5. 2026LatentBurst: A Fast and Efficient Multi Frame Super-Resolution for Hexadeca-Bayer Pattern CIS imagescited by 0
  6. 2026The Need for Neural ISP in the Small-Pixel Era: How Shrinking Pixels Push Optics to the Limit and Neural Restoration Pushes Backcited by 0
  7. 2026Perceiving Better Moments: Cover Frame Reselection and Enhancement for Live Photos with the Live2K Datasetcited by 0