# USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting

arXiv: https://arxiv.org/abs/2411.10504 · HTML: https://mlsanity.com/paper/2411.10504/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 51 references that are in the map.
- First posted on arXiv 15 Nov 2024.

## Builds on (most cited first, 28 of 28)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Deblur-NeRF: Neural Radiance Fields from Blurry Images](https://mlsanity.com/paper/2111.14292/) (2021)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [XVFI: eXtreme Video Frame Interpolation](https://mlsanity.com/paper/2103.16206/) (2021)
- [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)
- [E-NeRF: Neural Radiance Fields from a Moving Event Camera](https://mlsanity.com/paper/2208.11300/) (2022)
- [Event Enhanced High-Quality Image Recovery](https://mlsanity.com/paper/2007.08336/) (2020)
- [BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting](https://mlsanity.com/paper/2403.11831/) (2024)
- [Unifying Motion Deblurring and Frame Interpolation with Events](https://mlsanity.com/paper/2203.12178/) (2022)
- [A Retina-inspired Sampling Method for Visual Texture Reconstruction](https://mlsanity.com/paper/1907.08769/) (2019)
- [Deformable Neural Radiance Fields using RGB and Event Cameras](https://mlsanity.com/paper/2309.08416/) (2023)
- [1000x Faster Camera and Machine Vision with Ordinary Devices](https://mlsanity.com/paper/2201.09302/) (2022)
- [E-CIR: Event-Enhanced Continuous Intensity Recovery](https://mlsanity.com/paper/2203.01935/) (2022)
- [Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion](https://mlsanity.com/paper/2406.02972/) (2024)
- [Generalizing Event-Based Motion Deblurring in Real-World Scenarios](https://mlsanity.com/paper/2308.05932/) (2023)
- [EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting](https://mlsanity.com/paper/2405.14959/) (2024)
- [EvDNeRF: Reconstructing Event Data with Dynamic Neural Radiance Fields](https://mlsanity.com/paper/2310.02437/) (2023)
- [BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Stream](https://mlsanity.com/paper/2407.02174/) (2024)
- [EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting](https://mlsanity.com/paper/2410.15392/) (2024)
- [SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream](https://mlsanity.com/paper/2403.11222/) (2024)
- [SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams](https://mlsanity.com/paper/2403.09486/) (2024)
- [SpikeGS: 3D Gaussian Splatting from Spike Streams with High-Speed Camera Motion](https://mlsanity.com/paper/2407.10062/) (2024)
- [Unveiling the Potential of Spike Streams for Foreground Occlusion Removal from Densely Continuous Views](https://mlsanity.com/paper/2307.00821/) (2023)
- [SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors](https://mlsanity.com/paper/2407.03771/) (2024)
- [SpikeNVS: Enhancing Novel View Synthesis from Blurry Images via Spike Camera](https://mlsanity.com/paper/2404.06710/) (2024)
- [SpikeMM: Flexi-Magnification of High-Speed Micro-Motions](https://mlsanity.com/paper/2406.00383/) (2024)

## Built on by (most cited first, 3 of 3)

- [E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras](https://mlsanity.com/paper/2508.09912/) (2025)
- [GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation](https://mlsanity.com/paper/2505.15287/) (2025)
- [DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream](https://mlsanity.com/paper/2510.07752/) (2025)

## Abstract (arXiv)

Spike cameras, as an innovative neuromorphic camera that captures scenes with the 0-1 bit stream at 40 kHz, are increasingly employed for the 3D reconstruction task via Neural Radiance Fields (NeRF) or 3D Gaussian Splatting (3DGS). Previous spike-based 3D reconstruction approaches often employ a casecased pipeline: starting with high-quality image reconstruction from spike streams based on established spike-to-image reconstruction algorithms, then progressing to camera pose estimation and 3D reconstruction. However, this cascaded approach suffers from substantial cumulative errors, where quality limitations of initial image reconstructions negatively impact pose estimation, ultimately degrading the fidelity of the 3D reconstruction. To address these issues, we propose a synergistic optimization framework, USP-Gaussian, that unifies spike-based image reconstruction, pose correction, and Gaussian splatting into an end-to-end framework. Leveraging the multi-view consistency afforded by 3DGS and the motion capture capability of the spike camera, our framework enables a joint iterative optimization that seamlessly integrates information between the spike-to-image network and 3DGS. Experiments on synthetic datasets with accurate poses demonstrate that our method surpasses previous approaches by effectively eliminating cascading errors. Moreover, we integrate pose optimization to achieve robust 3D reconstruction in real-world scenarios with inaccurate initial poses, outperforming alternative methods by effectively reducing noise and preserving fine texture details. Our code, data and trained models will be available at https://github.com/chenkang455/USP-Gaussian.