mlsanityData to 14 Oct 2026

NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results

arXiv 2505.12089 ↗First posted 17 May 2025eess.IV cs.AI cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper reviews the NTIRE 2025 Efficient Burst HDR and Restoration Challenge, which aims to advance efficient multi-frame high dynamic range (HDR) and restoration techniques. The challenge is based on a novel RAW multi-frame fusion dataset, comprising nine noisy and misaligned RAW frames with various exposure levels per scene. Participants were tasked with developing solutions capable of effectively fusing these frames while adhering to strict efficiency constraints: fewer than 30 million model parameters and a computational budget under 4.0 trillion FLOPs. A total of 217 participants registered, with six teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 43.22 dB, showcasing the potential of novel methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers and practitioners in efficient burst HDR and restoration.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 72 of its 114 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

72 of 114 references.

References · 72

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  6. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  7. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  8. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  9. 2017Deformable Convolutional Networkscited by 1,488
  10. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  11. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  12. 2021Multi-Stage Progressive Image Restorationcited by 816
38 more
  1. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  2. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  3. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 424
  4. 2018Scale-recurrent Network for Deep Image Deblurringcited by 333
  5. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  6. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  7. 2018Unprocessing Images for Learned Raw Denoisingcited by 250
  8. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 228
  9. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 213
  10. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  11. 2017Burst Denoising with Kernel Prediction Networkscited by 157
  12. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 132
  13. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillationcited by 110
  14. 2019Handheld Multi-Frame Super-Resolutioncited by 85
  15. 2021Deep Burst Super-Resolutioncited by 83
  16. 2021Intriguing Findings of Frequency Selection for Image Deblurringcited by 81
  17. 2021Temporal Memory Relation Network for Workflow Recognition from Surgical Videocited by 66
  18. 2021Improving Image Restoration by Revisiting Global Information Aggregationcited by 61
  19. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  20. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  21. 2017Deep Burst Denoisingcited by 49
  22. 2022NAN: Noise-Aware NeRFs for Burst-Denoisingcited by 48
  23. 2024DarkIR: Robust Low-Light Image Restorationcited by 48
  24. 2019Basis Prediction Networks for Effective Burst Denoising with Large Kernelscited by 46
  25. 2020HighRes-net: Recursive Fusion for Multi-Frame Super-Resolution of Satellite Imagerycited by 42
  26. 2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
  27. 2024NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 40
  28. 2023Improving Image Restoration through Removing Degradations in Textual Representationscited by 36
  29. 2022BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignmentcited by 32
  30. 2023Burstormer: Burst Image Restoration and Enhancement Transformercited by 32
  31. 2023RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Imagecited by 32
  32. 2019Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentationcited by 30
  33. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  34. 2025The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Reportcited by 26
  35. 2025NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Resultscited by 25
  36. 2024See More Details: Efficient Image Super-Resolution by Experts Miningcited by 23
  37. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  38. 2025NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 22

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 4.

14 papers.

Sort:

  1. 2025NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Resultscited by 9
  2. 2025NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolutioncited by 9
  3. 2025NTIRE 2025 challenge on Text to Image Generation Model Quality Assessmentcited by 8
  4. 2025NTIRE 2025 XGC Quality Assessment Challenge: Methods and Resultscited by 6
  5. 2025NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challengecited by 5
  6. 2025RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Reportcited by 4
  7. 2026It Takes Two: A Duet of Periodicity and Directionality for Burst Flicker Removalcited by 4
  8. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  9. 2025Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Reportcited by 2
  10. 2025NTIRE 2025 Image Shadow Removal Challenge Reportcited by 1
  11. 2025NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Resultscited by 1
  12. 2026InstantHDR: Single-forward Gaussian Splatting Initialization for HDR 3D Reconstructioncited by 0
2 more
  1. 2026DRIFT: Deep Restoration, ISP Fusion, and Tone-mappingcited by 0
  2. 2026Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Bandingcited by 0