mlsanityData to 14 Oct 2026

The First Controllable Bokeh Rendering Challenge at NTIRE 2026

arXiv 2605.05510 ↗First posted 6 May 2026cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

This study presents the outcomes of the first Controllable Bokeh Rendering Challenge at NTIRE and highlights the most effective submitted methodologies. In total, 44 participants registered for the competition, of which 8 teams submitted valid solutions after the conclusion of the final test phase. All submissions were evaluated on unseen images, focusing on portraits and intricate subjects with complex and visually appealing bokeh phenomena. In addition to the first track focusing on established quantitative fidelity metrics, we conducted a qualitative user study with a panel of experts for a second track focusing on perceptual assessment. As this was the inaugural challenge on this topic, most of the participants focused on refining and extending the Bokehlicious baseline method.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 43 of its 75 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

43 of 75 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2024Depth Anything V2cited by 1,422
  6. 2022Simple Baselines for Image Restorationcited by 708
  7. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  8. 2018Synthetic Depth-of-Field with a Single-Camera Mobile Phonecited by 71
  9. 2021Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platformcited by 66
  10. 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
  11. 2015Seven ways to improve example-based single image super resolutioncited by 51
  12. 2022BokehMe: When Neural Rendering Meets Classical Renderingcited by 48
31 more
  1. 2017Fast Deep Matting for Portrait Animation on Mobile Phonecited by 30
  2. 2019Synthetic Defocus and Look-Ahead Autofocus for Casual Videographycited by 28
  3. 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
  4. 2019SteReFo: Efficient Image Refocusing with Stereo Visioncited by 25
  5. 2026The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Reportcited by 25
  6. 2021Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Imagecited by 18
  7. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  8. 2022MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effectscited by 17
  9. 2026NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Resultscited by 16
  10. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)cited by 16
  11. 2026NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methodscited by 15
  12. 2026NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Resultscited by 14
  13. 2026NTIRE 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Resultscited by 14
  14. 2026The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Resultscited by 13
  15. 2026The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Resultscited by 13
  16. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)cited by 12
  17. 2026NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)cited by 12
  18. 2025Bokehlicious: Photorealistic Bokeh Rendering with Controllable Aperturescited by 11
  19. 2026The Fourth Challenge on Image Super-Resolution (×4) at NTIRE 2026: Benchmark Results and Method Overviewcited by 10
  20. 2026NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Resultscited by 10
  21. 2025Score-based Self-supervised MRI Denoisingcited by 9
  22. 2023Defocus to focus: Photo-realistic bokeh rendering by fusing defocus and radiance priorscited by 8
  23. 2025BokehDiff: Neural Lens Blur with One-Step Diffusioncited by 8
  24. 2026NTIRE 2026 Rip Current Detection and Segmentation (RipDetSeg) Challenge Reportcited by 8
  25. 2026Low Light Image Enhancement Challenge at NTIRE 2026cited by 7
  26. 2026The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overviewcited by 7
  27. 2026The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overviewcited by 6
  28. 2026Robust Deepfake Detection, NTIRE 2026 Challenge: Reportcited by 6
  29. 2025Generative Refocusing: Flexible Defocus Control from a Single Imagecited by 4
  30. 2022Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokehcited by 3
  31. 2025BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matchingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The Third Challenge on Image Denoising at NTIRE 2026: Methods and Resultscited by 1
  2. 2026NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challengecited by 0