We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online depth refinement module leveraging self-supervision, and a global mapping module via TSDF fusion. The proposed system is online by design and achieves great robustness and accuracy via: (i) a robustified hybrid SLAM that incorporates learning-based optical flow and/or depth; (ii) self-supervised losses that leverage SLAM outputs and enforce long-term geometric consistency; (iii) careful system design that avoids degenerate cases in online depth refinement. We extensively evaluate GeoRefine on multiple public datasets and reach as low as $5\%$ absolute relative depth errors.
翻译:我们提出了一个以单星序列进行与几何相容密密测绘的强大和准确的深度改进系统,名为GeoRefine。GeoRefine由三个模块组成:一个使用学习前科的混合SLAM模块,一个利用自我监督的在线深度改进模块,以及通过TSDF聚合的全球测绘模块。拟议系统设计成在线,通过下列方式实现高度稳健和准确性:(一) 一个包含学习光学流动和/或深度的精密混合SLAM;(二) 自我监督的损失,利用SLAM产出,实施长期的几何一致性;(三) 谨慎的系统设计,避免在线深度完善的退化案例。我们广泛评价多个公共数据集上的GeoRefine,并达到5美元绝对相对深度误差的低点。