Fix incomplete 3D depth data by using RGB image and GAN with RDF-GAN
Fix incomplete 3D depth data by using RGB image and GAN with RDF-GAN
RGB-Depth Fusion GAN for Indoor Depth Completion
arXiv paper abstract https://arxiv.org/abs/2203.10856v1
arXiv PDF paper https://arxiv.org/pdf/2203.10856v1.pdf
… depth image … usually has an extensive range of missing depth values
… design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map.
The first branch employs an encoder-decoder structure to regress the local dense depth values from the raw depth map, with the help of … the RGB image.
In the other branch, … propose an RGB-depth fusion GAN to transfer the RGB image to the fine-grained textured depth map.
… adopt adaptive fusion modules named W-AdaIN to propagate the features across the two branches, and … append a confidence fusion head to fuse the two outputs of the branches for the final depth map.
… demonstrate … method … improves the depth completion performance, especially in a more realistic setting of indoor environments with the help of the pseudo depth map.
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
