Get better depth from monocular images by using segmentation masks with MaskDepth
--
Get better depth from monocular images by using segmentation masks with MaskDepth
Layered Depth Refinement with Mask Guidance
arXiv paper abstract https://arxiv.org/abs/2206.03048
arXiv PDF paper https://arxiv.org/pdf/2206.03048.pdf
Project page https://sooyekim.github.io/MaskDepth/
Depth maps … predicted by single image depth estimation (SIDE) models often fail to capture isolated holes in objects and/or have inaccurate boundary regions.
… high-quality masks are much easier to obtain, using commercial auto-masking tools or off-the-shelf methods of segmentation and matting or even by manual editing.
… formulate a novel problem of mask-guided depth refinement that utilizes a generic mask to refine the depth prediction of SIDE models.
… framework performs layered refinement and inpainting/outpainting, decomposing the depth map into two separate layers signified by the mask and the inverse mask.
As datasets with both depth and mask annotations are scarce, … propose a self-supervised learning scheme that uses arbitrary masks and RGB-D datasets.
… method is robust to different types of masks and initial depth predictions, accurately refining depth values in inner and outer mask boundary regions …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
