GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

• URL: http://arxiv.org/abs/2505.15287v1
• Date: Wed, 21 May 2025 09:15:42 GMT
• Title: GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation
• Abstract summary: We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks.<n>Results on event-based 3D reconstruction demonstrate GS2E's superior generalization capabilities and its practical value.
• Score: 32.13436507983477
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We introduce GS2E (Gaussian Splatting to Event), a large-scale synthetic event dataset for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB videos, which typically lack viewpoint diversity and geometric consistency, or depend on expensive, difficult-to-scale hardware setups. GS2E overcomes these limitations by first reconstructing photorealistic static scenes using 3D Gaussian Splatting, and subsequently employing a novel, physically-informed event simulation pipeline. This pipeline generally integrates adaptive trajectory interpolation with physically-consistent event contrast threshold modeling. Such an approach yields temporally dense and geometrically consistent event streams under diverse motion and lighting conditions, while ensuring strong alignment with underlying scene structures. Experimental results on event-based 3D reconstruction demonstrate GS2E's superior generalization capabilities and its practical value as a benchmark for advancing event vision research.

Related papers

• ERF-GS: Reconstructing Fast Motion from Disjoint Event-RGB Viewpoints [37.08264457707477]
  Event-RGB fusion Gaussian splatting (ERF-GS) framework integrates event information into both optimization and densification stages.<n>ERF-GS was developed using realistic simulation settings and realizes event-based learning detached from RGB inputs.<n>Our experiments show that ERF-GS outperforms both the 4DGS baseline and the concurrent E-D3DGS on different variants of the Neu3D and Nvidia datasets.
  arXiv  Detail & Related papers  (2026-08-09T07:00:27Z)
• Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing [55.13802890769086]
  We present Evita, the first unified backbone specifically engineered for dedicated dense RGB-Event parsing.<n>To achieve profound modal synergy, Evita embeds a suite of intrinsic co-learning modules directly into every encoder layer.<n>Evita establishes new state-of-the-art metrics while delivering a superior accuracy-latency trade-off for real-time multimodal perception.
  arXiv  Detail & Related papers  (2026-07-10T06:52:09Z)
• EventGait: Towards Robust Gait Recognition with Event Streams [50.890621860023]
  Event cameras offer microsecond temporal resolution and high dynamic range, naturally capturing robust dynamic cues and suppressing static noise.<n>We propose textbfEventGait, an end-to-end dual-stream framework that separately models motion and shape while preserving the advantages of events.<n>Our approach sets a new state of the art on both synthesized and real-world event-based gait benchmarks, highlighting the robustness and potential of event-driven gait analysis.
  arXiv  Detail & Related papers  (2026-05-21T08:12:04Z)
• AsyncEvGS: Asynchronous Event-Assisted Gaussian Splatting for Handheld Motion-Blurred Scenes [30.960288956042163]
  We introduce a flexible, high-resolution asynchronous RGB-Event dual-camera system and a corresponding reconstruction framework.<n>We employ a structure-driven event loss and view-specific consistency regularizers to mitigate the ill-posed behavior of traditional event losses.<n> Experiments demonstrate that our method achieves state-of-the-art performance on both our challenging dataset and existing benchmarks.
  arXiv  Detail & Related papers  (2026-05-08T03:39:45Z)
• EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes [31.16499311793949]
  E3R is a novel geometry estimation framework that augments pointmap-based reconstruction with asynchronous event streams.<n>EAG3R significantly outperforms state-of-the-art RGB-only baselines across monocular depth estimation, camera pose tracking, and dynamic reconstruction tasks.
  arXiv  Detail & Related papers  (2025-11-30T08:05:28Z)
• Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streams [34.02850677061797]
  Ev4DGS is the first approach for novel view rendering of non-rigidly deforming objects in the explicit observation space.<n>Our method regresses a deformable 3D Gaussian Splatting representation through 1) a loss relating the outputs of the estimated model with the 2D event observation space, and 2) a coarse 3D deformation model trained from binary masks generated from events.
  arXiv  Detail & Related papers  (2025-10-13T17:59:55Z)
• DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream [46.467919920459536]
  This paper introduces a novel framework that jointly optimize Dynamic 3DGS from the two modalities.<n>The key idea is to adopt event motion priors to guide the optimization of the deformation fields.<n>Our method outperforms existing image and event-based approaches across synthetic and real scenes.
  arXiv  Detail & Related papers  (2025-10-09T03:43:27Z)
• EventTracer: Fast Path Tracing-based Event Stream Rendering [22.899799024836586]
  EventTracer is a path tracing-based rendering pipeline that simulates high-fidelity event sequences from complex 3D scenes.<n>We show in two downstream tasks that EventTracer captures better scene details and demonstrates a greater similarity to real-world event data than other event simulators.
  arXiv  Detail & Related papers  (2025-08-25T14:33:09Z)
• HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis [59.25751939710903]
  We propose a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos.<n>Our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately.<n>Results highlight a practical and scalable solution for EVS in real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-24T03:54:40Z)
• HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting [47.67153284714988]
  We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per image.<n>We also propose a straightforward yet effective multi-stage training strategy to ensure robust training and high-quality view synthesis.<n> Experiments on benchmark datasets show our state-of-the-art performance of novel view synthesis in both indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2024-12-05T03:20:35Z)
• DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [71.61083731844282]
  We present DeSiRe-GS, a self-supervised gaussian splatting representation. It enables effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
  arXiv  Detail & Related papers  (2024-11-18T05:49:16Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting [72.60992807941885]
  Event cameras, inspired by biological vision, record pixel-wise intensity changes asynchronously with high temporal resolution.<n>We propose Event-Aided Free-Trajectory 3DGS, which seamlessly integrates the advantages of event cameras into 3DGS.<n>We evaluate our method on the public Tanks and Temples benchmark and a newly collected real-world dataset, RealEv-DAVIS.
  arXiv  Detail & Related papers  (2024-10-20T13:44:24Z)
• Elite-EvGS: Learning Event-based 3D Gaussian Splatting by Distilling Event-to-Video Priors [8.93657924734248]
  Event cameras are bio-inspired sensors that output asynchronous and sparse event streams, instead of fixed frames. We propose a novel event-based 3DGS framework, named Elite-EvGS. Our key idea is to distill the prior knowledge from the off-the-shelf event-to-video (E2V) models to effectively reconstruct 3D scenes from events.
  arXiv  Detail & Related papers  (2024-09-20T10:47:52Z)
• E2GS: Event Enhanced Gaussian Splatting [9.096805985896625]
  Event Enhanced Gaussian Splatting (E2GS) is a novel method that incorporates event data into Gaussian Splatting. Our E2GS effectively utilizes both blurry images and event data, significantly improving image deblurring and producing high-quality novel view synthesis.
  arXiv  Detail & Related papers  (2024-06-21T08:43:47Z)
• Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion [54.197343533492486]
  Event3DGS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.
  arXiv  Detail & Related papers  (2024-06-05T06:06:03Z)
• EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting [5.160735014509357]
  We propose the first event-based generalizable 3D reconstruction framework, called EvGGS. It reconstructs scenes as 3D Gaussians from only event input in a feedforward manner. Our approach performs better than all baselines in reconstruction quality, and depth/intensity predictions with satisfactory speed.
  arXiv  Detail & Related papers  (2024-05-23T18:10:26Z)
• GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
  GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
  arXiv  Detail & Related papers  (2024-02-15T17:32:50Z)
• Implicit Event-RGBD Neural SLAM [54.74363487009845]
  Implicit neural SLAM has achieved remarkable progress recently. Existing methods face significant challenges in non-ideal scenarios. We propose EN-SLAM, the first event-RGBD implicit neural SLAM framework.
  arXiv  Detail & Related papers  (2023-11-18T08:48:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.