EventNeuS: 3D Mesh Reconstruction from a Single Event Camera
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910010613694464 |
|---|---|
| author | Sachan, Shreyas Rudnev, Viktor Elgharib, Mohamed Theobalt, Christian Golyanik, Vladislav |
| author_facet | Sachan, Shreyas Rudnev, Viktor Elgharib, Mohamed Theobalt, Christian Golyanik, Vladislav |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03847 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EventNeuS: 3D Mesh Reconstruction from a Single Event Camera Sachan, Shreyas Rudnev, Viktor Elgharib, Mohamed Theobalt, Christian Golyanik, Vladislav Computer Vision and Pattern Recognition 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. |
| title | EventNeuS: 3D Mesh Reconstruction from a Single Event Camera |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.03847 |