EventNeuS: 3D Mesh Reconstruction from a Single Event Camera
Not on the map. Why?
Abstract (arXiv)
Event cameras offer a considerable alternative to RGB cameras in many scenarios. While there are recent works on event-based novel-view synthesis, dense 3D mesh reconstruction remains scarcely explored and existing event-based techniques are severely limited in their 3D reconstruction accuracy. To address this limitation, we present EventNeuS, a self-supervised neural model for learning 3D representations from monocular colour event streams. Our approach, for the first time, combines 3D signed distance function and density field learning with event-based supervision. Furthermore, we introduce spherical harmonics encodings into our model for enhanced handling of view-dependent effects. EventNeuS outperforms existing approaches by a significant margin, achieving 34% lower Chamfer distance and 31% lower mean absolute error on average compared to the best previous method.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 3 Feb 2026.
Builds on
34 of 42 references.
References · 34
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
- 2021Volume Rendering of Neural Implicit Surfacescited by 990
- 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
- 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
- 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
- 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
- 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
- 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 191
- 2020Event-based Stereo Visual Odometrycited by 105
- 2022EventNeRF: Neural Radiance Fields from a Single Colour Event Cameracited by 92
- 2022Event-aided Direct Sparse Odometrycited by 91
22 more
- 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
- 2023Detector-Free Structure from Motioncited by 71
- 2022E-NeRF: Neural Radiance Fields from a Moving Event Cameracited by 70
- 2018Semi-Dense 3D Reconstruction with a Stereo Event Cameracited by 67
- 2024Recent Event Camera Innovations: A Surveycited by 67
- 2019EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Cameracited by 65
- 2022Ev-NeRF: Event Based Neural Radiance Fieldcited by 59
- 2022Critical Regularizations for Neural Surface Reconstruction in the Wildcited by 51
- 2020EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Streamcited by 48
- 2023Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motioncited by 44
- 2021EventHPE: Event-based 3D Human Pose and Shape Estimationcited by 42
- 2024Mitigating Motion Blur in Neural Radiance Fields with Events and Framescited by 31
- 2024EventEgo3D: 3D Human Motion Capture from Egocentric Event Streamscited by 29
- 20233D Pose Estimation of Two Interacting Hands from a Monocular Event Cameracited by 17
- 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
- 2024BeNeRF: Neural Radiance Fields from a Single Blurry Image and Event Streamcited by 15
- 2023EvAC3D: From Event-based Apparent Contours to 3D Models via Continuous Visual Hullscited by 11
- 2024Physical Priors Augmented Event-Based 3D Reconstructioncited by 11
- 2024Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditionscited by 10
- 2025EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Cameracited by 6
- 2025Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streamscited by 3
- 2023Multi-View Stereo Representation Revisit: Region-Aware MVSNetcited by 2
Built on by
Not cited yet.