arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.36610cs.CV
收藏

基于事件相机与RGB的4D重建

4D Reconstruction with Events & RGB

Singapore-MIT Alliance for Research & Technology Centre(新加坡-麻省理工研究与技术联盟);Singapore Management University(新加坡管理大学);Massachusetts Institute of Technology(麻省理工学院)

Dulanga Weerakoon, Darshana Rathnayake, Van Minh Do, Hemanth Sabbella, Kaichen Zhou, Fangneng Zhan, Alok Prakash, Sanjay E. Sarma, Archan Misra, Paul Pu Liang

AI总结:

本研究在仅RGB的4D重建模型Monst3R中加入事件相机输入分支,在3个基准数据集上使Abs Rel平均降低3.4%,高运动场景下增益最大,证明轻量级RGB-事件融合可提升4D重建鲁棒性。

摘要:

从单台运动相机重建随时间变化的动态3D场景(4D重建)是机器人技术与AR/VR应用的核心,但当前最先进的前馈方法仅依赖RGB帧,因此继承了传统相机的失效模式,包括在相机或物体快速或非均匀运动下的运动模糊与时间混叠。事件相机以微秒级分辨率异步报告每个像素的亮度变化,提供了对这些伪影基本免疫的互补信号,但该模态能否在不彻底重新设计架构的情况下融入现有基于RGB的4D重建管线仍是开放问题。在这项初步研究中,我们探究了一种最小扩展方案:我们为仅基于RGB的现有4D重建模型Monst3R增加了一个额外的事件相机输入分支,其余架构保持不变。在3个基准数据集上,这种简单的RGB-事件融合相比仅基于RGB的Monst3R基线平均降低了3.4%的Abs Rel(绝对相对误差),敏感性分析显示,改进效果随相机与物体运动幅度增大而提升,在仅RGB重建性能最差的高物体运动条件下观察到最大增益。这些早期结果表明,即使是轻量级、非侵入式的事件数据融合也能显著提升4D重建的鲁棒性,为未来更深入的架构研究提供了动机。

英文摘要:

Reconstructing dynamic 3D scenes over time (4D reconstruction) from a single moving camera is central to robotics and AR/VR applications, yet state-of the-art feed-forward methods rely solely on RGB frames and therefore inherit the failure modes of conventional cameras, including motion blur and temporal aliasing under fast or non-uniform camera and object motion. Event cameras report per-pixel brightness changes asynchronously at microsecond resolution, offering a complementary signal that is largely immune to these artifacts, but whether this modality can be incorporated into existing RGB based 4D reconstruction pipelines without a full architectural redesign remains an open question. In this preliminary study, we investigate a minimal extension: we augment Monst3R, an existing RGB-only 4D reconstruction model, with an additional event-camera input branch, leaving the rest of the architecture unchanged. Across 3 benchmark datasets, this simple RGB-event fusion reduces Abs Rel by 3.4% on average relative to the RGB-only Monst3R baseline, and a sensitivity analysis shows that the improvement grows with the magnitude of camera and object motion, with the largest gains observed under high object motion conditions where RGB-only reconstruction degrades most. These early results suggest that even a lightweight, non-invasive fusion of event data can meaningfully improve 4D reconstruction robustness, motivating a more thorough architectural investigation in future work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑