# EBAD-Gaussian: Event-driven Bundle Adjusted Deblur Gaussian Splatting

arXiv: https://arxiv.org/abs/2504.10012 · HTML: https://mlsanity.com/paper/2504.10012/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 19 of 19)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [gsplat: An Open-Source Library for Gaussian Splatting](https://mlsanity.com/paper/2409.06765/) (2024)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [3D Gaussian Splatting as Markov Chain Monte Carlo](https://mlsanity.com/paper/2404.09591/) (2024)
- [Deblur-NeRF: Neural Radiance Fields from Blurry Images](https://mlsanity.com/paper/2111.14292/) (2021)
- [HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting](https://mlsanity.com/paper/2403.12722/) (2024)
- [Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera](https://mlsanity.com/paper/1811.10180/) (2018)
- [EventNeRF: Neural Radiance Fields from a Single Colour Event Camera](https://mlsanity.com/paper/2206.11896/) (2022)
- [BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields](https://mlsanity.com/paper/2211.12853/) (2022)
- [DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors](https://mlsanity.com/paper/2211.12046/) (2022)
- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [Ev-NeRF: Event Based Neural Radiance Field](https://mlsanity.com/paper/2206.12455/) (2022)
- [Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion](https://mlsanity.com/paper/2309.08596/) (2023)
- [Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle](https://mlsanity.com/paper/2407.19548/) (2024)
- [Deblurring Neural Radiance Fields with Event-driven Bundle Adjustment](https://mlsanity.com/paper/2406.14360/) (2024)
- [Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions](https://mlsanity.com/paper/2409.17988/) (2024)

## Built on by (most cited first, 6 of 6)

- [GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation](https://mlsanity.com/paper/2505.15287/) (2025)
- [A Survey of 3D Reconstruction with Event Cameras](https://mlsanity.com/paper/2505.08438/) (2025)
- [EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering](https://mlsanity.com/paper/2511.16542/) (2025)
- [EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting](https://mlsanity.com/paper/2604.22183/) (2026)
- [Geometric-Photometric Event-based 3D Gaussian Ray Tracing](https://mlsanity.com/paper/2512.18640/) (2025)
- [JADE-GS: Joint Allocation of Deblurring Evidence for Event-Assisted 3D Gaussian Splatting](https://mlsanity.com/paper/2607.14990/) (2026)

## Abstract (arXiv)

While 3D Gaussian Splatting (3D-GS) achieves photorealistic novel view synthesis, its performance degrades with motion blur. In scenarios with rapid motion or low-light conditions, existing RGB-based deblurring methods struggle to model camera pose and radiance changes during exposure, reducing reconstruction accuracy. Event cameras, capturing continuous brightness changes during exposure, can effectively assist in modeling motion blur and improving reconstruction quality. Therefore, we propose Event-driven Bundle Adjusted Deblur Gaussian Splatting (EBAD-Gaussian), which reconstructs sharp 3D Gaussians from event streams and severely blurred images. This method jointly learns the parameters of these Gaussians while recovering camera motion trajectories during exposure time. Specifically, we first construct a blur loss function by synthesizing multiple latent sharp images during the exposure time, minimizing the difference between real and synthesized blurred images. Then we use event stream to supervise the light intensity changes between latent sharp images at any time within the exposure period, supplementing the light intensity dynamic changes lost in RGB images. Furthermore, we optimize the latent sharp images at intermediate exposure times based on the event-based double integral (EDI) prior, applying consistency constraints to enhance the details and texture information of the reconstructed images. Extensive experiments on synthetic and real-world datasets show that EBAD-Gaussian can achieve high-quality 3D scene reconstruction under the condition of blurred images and event stream inputs.