Event3R：通过时空特征聚合从事件相机进行异步到全局的3D重建
Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation
浏览论文内容
中文总结 AI 辅助
研究针对事件相机异步、稀疏和高动态特性及缺乏标注数据集的问题，提出Event3R框架，通过时空体素表示、时间注意力模块、掩码箱建模策略及对比对齐和一致性正则化损失，实现鲁棒的3D重建，性能显著优于现有方法。
中文摘要 AI 辅助
鲁棒的3D重建对机器人技术和实体感知至关重要。像DUSt3R这样的前馈方法在从RGB图像进行密集3D重建方面取得了显著进展。但将此类密集3D重建扩展到事件相机仍具挑战性，因其异步、稀疏和高动态特性以及缺乏大规模标注数据集。本文介绍Event3R，一个将异步事件流直接映射到全局一致3D点云的前馈框架。它将输入事件表示为时空体素，通过时间注意力模块实现时间感知特征整合。还提出掩码箱建模策略进行自监督预训练，微调时加入对比对齐和一致性正则化损失。实验表明Event3R实现了鲁棒、时间一致且全局对齐的3D重建，显著优于现有基于事件的方法。
英文摘要
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.
发表机构
- Zhejiang University（浙江大学）
- Westlake University（西湖大学）
机构由 AI 辅助整理，请以论文原文为准。
