Sharper depth from single image by using scene structure and details with CADepth-Net

Sharper depth from single image by using scene structure and details with CADepth-Net

Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation

arXiv paper abstract https://arxiv.org/abs/2112.13047v1

arXiv PDF paper https://arxiv.org/pdf/2112.13047v1.pdf

Self-supervised learning has shown very promising results for monocular depth estimation.

... Recent works ... lack of explicit modeling of scene structure and proper handling of details information, which leads to ... blurry artefacts in ... results.

... propose the Channel-wise Attention-based Depth Estimation Network (CADepth-Net) with two effective contributions:

1) The structure perception module employs the self-attention mechanism to capture long-range dependencies and aggregates discriminative features ...

2) The detail emphasis module re-calibrates channel-wise feature maps ... highlight crucial local details information and fuse different level features

... experiments validate the effectiveness of our method and show that our model achieves the state-of-the-art results on the KITTI benchmark and Make3D datasets.

Please like and share this post if you enjoyed it using the buttons at the bottom! 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 #ComputerVision #3D #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning