# Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation

arXiv: https://arxiv.org/abs/2607.15727 · HTML: https://mlsanity.com/paper/2607.15727/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 29 of 29)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [Events-to-Video: Bringing Modern Computer Vision to Event Cameras](https://mlsanity.com/paper/1904.08298/) (2019)
- [COLMAP-Free 3D Gaussian Splatting](https://mlsanity.com/paper/2312.07504/) (2023)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [EventNeRF: Neural Radiance Fields from a Single Colour Event Camera](https://mlsanity.com/paper/2206.11896/) (2022)
- [Learning Monocular Dense Depth from Events](https://mlsanity.com/paper/2010.08350/) (2020)
- [E-NeRF: Neural Radiance Fields from a Moving Event Camera](https://mlsanity.com/paper/2208.11300/) (2022)
- [Semi-Dense 3D Reconstruction with a Stereo Event Camera](https://mlsanity.com/paper/1807.07429/) (2018)
- [Ev-NeRF: Event Based Neural Radiance Field](https://mlsanity.com/paper/2206.12455/) (2022)
- [TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset](https://mlsanity.com/paper/2108.07329/) (2021)
- [Masked Event Modeling: Self-Supervised Pretraining for Event Cameras](https://mlsanity.com/paper/2212.10368/) (2022)
- [Deep Event Visual Odometry](https://mlsanity.com/paper/2312.09800/) (2023)
- [Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion](https://mlsanity.com/paper/2406.02972/) (2024)
- [EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting](https://mlsanity.com/paper/2405.14959/) (2024)
- [IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera](https://mlsanity.com/paper/2410.08107/) (2024)
- [Event-based Monocular Dense Depth Estimation with Recurrent Transformers](https://mlsanity.com/paper/2212.02791/) (2022)
- [EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering](https://mlsanity.com/paper/2412.07293/) (2024)
- [Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT](https://mlsanity.com/paper/2507.08448/) (2025)
- [DERD-Net: Learning Depth from Event-based Ray Densities](https://mlsanity.com/paper/2504.15863/) (2025)
- [PEOD: A Pixel-Aligned Event-RGB Benchmark for Object Detection under Challenging Conditions](https://mlsanity.com/paper/2511.08140/) (2025)
- [EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes](https://mlsanity.com/paper/2512.00771/) (2025)
- [CREPES: Cooperative RElative Pose Estimation System](https://mlsanity.com/paper/2302.01036/) (2023)

## Abstract (arXiv)

Robust 3D reconstruction is essential for robotics and embodied perception. Recent feed-forward approaches such as DUSt3R have demonstrated impressive progress in dense 3D reconstruction from RGB images, achieving global geometric consistency and strong generalization. However, extending such dense 3D reconstruction to event cameras remains challenging due to their asynchronous, sparse, and highly dynamic nature, as well as the lack of large-scale, well-labeled datasets. In this work, we introduce Event3R, a feed-forward framework that directly maps asynchronous event streams to globally consistent 3D point clouds. Event3R represents incoming events as spatial-temporal voxels, enabling time-aware feature integration through a temporal attention module that enhances the module's temporal feature learning. To further strengthen temporal representation learning and reduce reliance on labeled data, we propose a Masked Bin Modeling (MBM) strategy for self-supervised pre-training, enabling robust temporal representation learning with minimal labeled data, and retain it as an auxiliary fine-tuning objective. In addition, contrastive alignment and consistency regularization losses are incorporated during fine-tuning to reinforce structural correspondence and temporal coherence across views. Extensive experiments on both synthetic and real-world benchmarks demonstrate that Event3R achieves robust, temporally consistent, and globally aligned 3D reconstructions, significantly outperforming existing event-based methods.