SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors

TL;DR

SpikeGS introduces a novel framework that uses high-temporal-resolution spike streams from bio-inspired sensors to rapidly reconstruct detailed 3D scenes, overcoming limitations of traditional methods reliant on sharp images.

Contribution

This work is the first to integrate spike streams into 3D scene reconstruction, enabling fast, detailed 3D modeling with bio-inspired sensors in real-world scenarios.

Findings

Outperforms existing spike-based reconstruction methods

Reconstructs 3D scenes within 1 second

Effective on synthetic and real-world datasets

Abstract

3D Gaussian Splatting (3DGS) demonstrates unparalleled superior performance in 3D scene reconstruction. However, 3DGS heavily relies on the sharp images. Fulfilling this requirement can be challenging in real-world scenarios especially when the camera moves fast, which severely limits the application of 3DGS. To address these challenges, we proposed Spike Gausian Splatting (SpikeGS), the first framework that integrates the spike streams into 3DGS pipeline to reconstruct 3D scenes via a fast-moving bio-inspired camera. With accumulation rasterization, interval supervision, and a specially designed pipeline, SpikeGS extracts detailed geometry and texture from high temporal resolution but texture lacking spike stream, reconstructs 3D scenes captured in 1 second. Extensive experiments on multiple synthetic and real-world datasets demonstrate the superiority of SpikeGS compared with existing spike-based and deblur 3D scene reconstruction methods. Codes and data will be released soon.