We introduce a novel end-to-end deeplearning solution for rapidly estimating a dense spherical depth map of an indoor *** input is a single equirectangular image registered with a sparse depth map,as provided by a var...
详细信息
We introduce a novel end-to-end deeplearning solution for rapidly estimating a dense spherical depth map of an indoor *** input is a single equirectangular image registered with a sparse depth map,as provided by a variety of common capture *** is inferred by an efficient and lightweight single-branch network,which employs a dynamic gating system to process together dense visual data and sparse geometric *** exploit the characteristics of typical man-made environments to efficiently compress multiresolution features and find short-and long-range relations among scene ***,we introduce a new augmentation strategy to make the model robust to different types of sparsity,including those generated by various structured light sensors and LiDAR *** experimental results demonstrate that our method provides interactive performance and outperforms stateof-the-art solutions in computational efficiency,adaptivity to variable depth sparsity patterns,and prediction accuracy for challenging indoor data,even when trained solely on synthetic data without any fine tuning.
暂无评论