论文标题
稀疏SPN：稀疏关键的深度完成
Sparse SPN: Depth Completion from Sparse Keypoints
论文作者
论文摘要
我们的长期目标是使用基于图像的深度完成来快速从稀疏点云中创建3D模型，例如来自SFM或大满贯。深入完成了很多进展。但是，大多数当前作品都采用已知深度的分布良好的样本，例如激光雷达或随机均匀采样，并且由于较大的未采样区域而在不均匀的样品（例如来自Kepoints）上的性能较差。为了解决这个问题，我们通过多尺度预测和扩张的内核扩展了CSPN，从而使关键点采样深度的完善得多。我们还表明，在NYUV2上训练的模型通过完成稀疏的SFM点在ETH3D上产生了令人惊讶的好点云。
Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To address this problem, we extend CSPN with multiscale prediction and a dilated kernel, leading to much better completion of keypoint-sampled depth. We also show that a model trained on NYUv2 creates surprisingly good point clouds on ETH3D by completing sparse SfM points.
