arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2602.23559cs.CV

无需校准,无需深度,无需问题:跨传感器视角合成与3D一致性

No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency

Bosch Research North America(博世北美研究部);Bosch Center for Artificial Intelligence (BCAI)(博世人工智能中心)

Cho-Ying Wu, Zixun Huang, Xinyu Huang, Liu Ren

AI总结:

本文提出了一种无需校准的跨传感器视角合成方法,通过匹配、密集化和3D点云整合技术,解决RGB-X数据对齐问题,提升大规模真实世界数据收集的效率。

摘要:

我们首次研究了跨不同模态的跨传感器视角合成。我们探讨了一个实际、基础且常被忽视的问题:获取对齐的RGB-X数据,其中大多数RGB-X先前工作假设此类配对存在,并专注于模态融合,但实际需要大量的工程努力进行校准。我们提出了一种匹配-密集化-整合方法。首先,我们进行RGB-X图像匹配,随后进行引导点密集化。使用所提出的置信度感知密集化和自匹配过滤,我们实现了更好的视角合成,并在3D高斯点云(3DGS)中整合它们。我们的方法不使用X传感器的3D先验,并仅假设几乎无成本的COLMAP用于RGB。我们的目标是去除各种RGB-X传感器的繁琐校准,并通过一种可扩展的解决方案推动跨传感器学习的普及,从而突破大规模真实世界RGB-X数据收集的瓶颈。

英文摘要:

We present the first study of cross-sensor view synthesis across different modalities. We examine a practical, fundamental, yet widely overlooked problem: getting aligned RGB-X data, where most RGB-X prior work assumes such pairs exist and focuses on modality fusion, but it empirically requires huge engineering effort in calibration. We propose a match-densify-consolidate method. First, we perform RGB-X image matching followed by guided point densification. Using the proposed confidence-aware densification and self-matching filtering, we attain better view synthesis and later consolidate them in 3D Gaussian Splatting (3DGS). Our method uses no 3D priors for X-sensor and only assumes nearly no-cost COLMAP for RGB. We aim to remove the cumbersome calibration for various RGB-X sensors and advance the popularity of cross-sensor learning by a scalable solution that breaks through the bottleneck in large-scale real-world RGB-X data collection.

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。

↑