mlsanityData to 7 Oct 2026

Deblurring Neural Radiance Fields with Event-driven Bundle Adjustment

arXiv 2406.14360 ↗First posted 20 Jun 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRF) achieves impressive 3D representation learning and novel view synthesis results with high-quality multi-view images as input. However, motion blur in images often occurs in low-light and high-speed motion scenes, which significantly degrades the reconstruction quality of NeRF. Previous deblurring NeRF methods struggle to estimate pose and lighting changes during the exposure time, making them unable to accurately model the motion blur. The bio-inspired event camera measuring intensity changes with high temporal resolution makes up this information deficiency. In this paper, we propose Event-driven Bundle Adjustment for Deblurring Neural Radiance Fields (EBAD-NeRF) to jointly optimize the learnable poses and NeRF parameters by leveraging the hybrid event-RGB data. An intensity-change-metric event loss and a photo-metric blur loss are introduced to strengthen the explicit modeling of camera motion blur. Experiments on both synthetic and real-captured data demonstrate that EBAD-NeRF can obtain accurate camera trajectory during the exposure time and learn a sharper 3D representations compared to prior works.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 34 of its 57 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

34 of 57 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  4. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  5. 2019Event-based Vision: A Surveycited by 1,010
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  8. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  9. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  10. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  11. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  12. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
22 more
  1. 2021E-RAFT: Dense Optical Flow from Event Camerascited by 149
  2. 2018Bringing a Blurry Frame Alive at High Frame-Rate with an Event Cameracited by 141
  3. 2021Event-Based Fusion for Motion Deblurring with Cross-modal Attentioncited by 112
  4. 2021Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networkscited by 99
  5. 2022EventNeRF: Neural Radiance Fields from a Single Colour Event Cameracited by 92
  6. 2020Learning Event-Based Motion Deblurringcited by 81
  7. 2022DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priorscited by 70
  8. 2019EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Cameracited by 65
  9. 2022Ev-NeRF: Event Based Neural Radiance Fieldcited by 59
  10. 2021Motion Deblurring with Real Eventscited by 52
  11. 2023Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motioncited by 44
  12. 2021Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumescited by 41
  13. 2017Learning Blind Motion Deblurringcited by 36
  14. 2020Single Image Optical Flow Estimation with an Event Cameracited by 34
  15. 2023Deformable Neural Radiance Fields using RGB and Event Camerascited by 31
  16. 2024Mitigating Motion Blur in Neural Radiance Fields with Events and Framescited by 31
  17. 2018Real-time high speed motion prediction using fast aperture-robust event-driven visual flowcited by 24
  18. 2024Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Priorcited by 12
  19. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  20. 2019Learning Digital Camera Pipeline for Extreme Low-Light Imagingcited by 9
  21. 2016End-to-End Learning for Image Burst Deblurringcited by 6
  22. 2016Dynamic Scene Deblurring using a Locally Adaptive Linear Blur Modelcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 9; 2026: 5.

15 papers.

Sort:

By area:

  1. 2025DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splattingcited by 14
  2. 2025EBAD-Gaussian: Event-driven Bundle Adjusted Deblur Gaussian Splattingcited by 6
  3. 2025GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generationcited by 6
  4. 2024LSE-NeRF: Learning Sensor Modeling Errors for Deblured Neural Radiance Fields with RGB-Event Stereocited by 4
  5. 2025A Survey of 3D Reconstruction with Event Camerascited by 4
  6. 2025Event Camera Guided Visual Media Restoration & 3D Reconstruction: A Surveycited by 3
  7. 2025CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurringcited by 3
  8. 2025Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videoscited by 1
  9. 2026EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splattingcited by 1
  10. 2026AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenescited by 1
  11. 2025Is-NeRF: In-scattering Neural Radiance Field for Blurred Imagescited by 0
  12. 2025GeMS: Efficient Gaussian Splatting for Extreme Motion Blurcited by 0
3 more
  1. 2026Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Eventscited by 0
  2. 2026See Silhouettes in Motion with Neuromorphic Visioncited by 0
  3. 2026PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blurcited by 0