论文标题
Georefine：自制的在线深度精炼，以进行准确的密集映射
GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping
论文作者
论文摘要
我们提出了一个稳健而准确的深度细化系统，称为GeoreFine，用于从单眼序列中几何谐波密集的映射。 Georefine由三个模块组成：使用基于学习的先验的混合大满贯模块，在线深度细化模块利用自我upervision，以及通过TSDF融合的全局映射模块。拟议的系统是通过设计在线的，并通过以下方式实现了良好的鲁棒性和准确性：（i）鲁棒的杂种大满贯，结合了基于学习的光流和/或深度； （ii）利用大满贯产出并实施长期几何一致性的自制损失； （iii）仔细的系统设计，以避免在线深度细化中的案例退化。我们在多个公共数据集上广泛评估GeoreFine，并达到低至$ 5 \％$的绝对相对深度错误。
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.
