Get 3D scene in real-time from monocular images using depth uncertainty with Rosinol

Get 3D scene in real-time from monocular images using depth uncertainty with Rosinol

Probabilistic Volumetric Fusion for Dense Monocular SLAM

arXiv paper abstract https://arxiv.org/abs/2210.01276v1

arXiv PDF paper https://arxiv.org/pdf/2210.01276v1.pdf

... present a novel method to reconstruct 3D scenes from images by leveraging deep dense monocular SLAM and fast uncertainty propagation.

The proposed approach is able to 3D reconstruct scenes densely, accurately, and in real-time while being robust to extremely noisy depth estimates coming from dense monocular SLAM.

... probabilistic depth uncertainty derives directly from the information matrix of the underlying bundle adjustment problem in SLAM.

... resulting depth uncertainty provides an excellent signal to weight the depth-maps for volumetric fusion.

... approach generates an accurate 3D mesh with significantly fewer artifacts.

... achieves 92% better accuracy than directly fusing depths from monocular SLAM, and up to 90% improvements compared to the best competing approach.

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 LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #3D #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning