AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Spike4DGS: Towards High-Speed Dynamic Scene Rendering with 4D Gaussian Splatting via a Spike Camera Array

Qinghong Ye, Yiqian Chang, Jianing Li, Haoran Xu, Xuan Wang, Wei Zhang, Yonghong Tian, Peixi Peng

NeurIPS 2025 · 3D vision › Gaussian splatting · approach: Deformable 4D Gaussian splatting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Spike4DGS renders high-speed dynamic scenes with 4D Gaussian Splatting from a spike camera array, addressing the limits of monocular spike-based NeRF/3DGS methods for dynamic motion.

Problem

High-speed dynamic scene rendering from spike camera data; existing NeRF/3DGS spike methods target static scenes with a single monocular camera and struggle with dynamic motion and limited spatial coverage.

Approach

Uses a spike camera array with 4D Gaussian Splatting to exploit the high temporal resolution of spikes and the multi-view spatial coverage of the array to reconstruct fine details of dynamic scenes.

Experimental setup

Builds on: 3D Gaussian Splatting 4D Gaussian Splatting

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy