Get 3D shapes from a single color image

Get 3D shapes from a single color image

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

arXiv paper abstract https://arxiv.org/abs/2105.02047v1

arXiv PDF paper https://arxiv.org/pdf/2105.02047v1.pdf

GitHub https://github.com/fkluger/cuboids_revisited

... propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map. We condition the network on previously detected parts of the scene, thus parsing it one-by-one. To obtain 3D features from a single RGB image, we additionally optimise a feature extraction CNN in an end-to-end manner. ... propose an occlusion-aware distance metric correctly handling opaque scenes. ... algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the challenging NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.

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 #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning