mlsanityData to 14 Oct 2026

eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion Models

arXiv 2608.08519 ↗First posted 9 Aug 2026cs.CVcited by 0

On the map: Diffusion models → Video generation

Abstract (arXiv)

Intensity-image reconstruction from event streams remains a challenging problem due to the binary, sparse, and asynchronous nature of event data. This work proposes eBIRD, an event-guided reconstruction framework that combines a DDPM with ControlNet-based conditioning. We analyze generic and specialized diffusion learning strategies for handwritten digit (N-MNIST) and face (RGBE-Gaze) reconstruction using 33ms event windows. On N-MNIST, the general model achieves the best reconstruction quality (MSE 0.0052, SSIM 0.8982, PSNR 23.34dB), whereas the specialized model performs best on RGBE-Gaze (MSE 0.0161, SSIM 0.7605, PSNR 19.08dB). These preliminary results suggest that controllable diffusion models are a promising approach for event-guided intensity-image reconstruction, while highlighting that the preferred learning strategy depends on the reconstruction domain.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 13 of its 22 references that are in the map. First posted on arXiv 9 Aug 2026.

Builds on

13 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction15 Jul
  2. 2024E2VIDiff: Perceptual Events-to-Video Reconstruction using Diffusion Priors11 Jul

Other references · 11

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  7. 2019Event-based Vision: A Surveycited by 1,016
  8. 2019High Speed and High Dynamic Range Video with an Event Cameracited by 345
  9. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
  10. 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 193
  11. 2024Recent Event Camera Innovations: A Surveycited by 68

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models
  2. 2025IE2Video: Adapting Pretrained Diffusion Models for Event-Based Video Reconstruction
  3. 2026UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models
  4. 2025ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Models
  5. 2026EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction
  6. 2026Bridging Event Streams and DiT: Event-Guided Video Frame Interpolation
  7. 2024EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
  8. 2026LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models