Joint bilateral propagation upsampling for unstructured multi-view stereo

Mengqiang Wei, Qingan Yan, Fei Luo, Chengfang Song, Chunxia Xiao

Abstract: In this paper, we explore a new way to accelerate and densify unstructured multi-view stereo (MVS). While many unstructured MVS algorithms have been proposed, we discover that the image-guided resizing can easily and significantly benefit their 3D reconstruction results in both efficiency and completeness. Therefore, we build our framework upon a novel selective joint bilateral upsampling and depth propagation strategy. First, we downsample the input unstructured images into lower resolution ones and perform the MVS calculation to efficiently obtain depth and normal maps from these resized pictures. Then, the proposed algorithm upsamples the normal maps with the guidance of input images, and jointly take them into consideration to recover the low-resolution depth maps into high resolution with geometry details simultaneously enriched. Finally by adaptively fusing the reconstructed depth and normal maps, we construct the final dense 3D scene. Quantitative results validate the efficiency and effectiveness of the proposed method.