Better object orientation using self-supervision by learning textures with TexPose
Better object orientation using self-supervision by learning textures with TexPose
TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation
arXiv paper abstract https://arxiv.org/abs/2212.12902
arXiv PDF paper https://arxiv.org/pdf/2212.12902.pdf
… introduce neural texture learning for 6D object pose estimation from synthetic data and a few unlabelled real images.
… major contribution is a novel learning scheme which removes the drawbacks of previous works, namely the strong dependency on co-modalities or additional refinement.
… formulate such a scheme as two sub-optimisation problems on texture learning and pose learning.
… separately learn to predict realistic texture of objects from real image collections and learn pose estimation from pixel-perfect synthetic data.
Combining these two capabilities allows then to synthesise photorealistic novel views to supervise the pose estimator with accurate geometry.
… approach significantly outperforms the recent state-of-the-art methods without ground-truth pose annotations and demonstrates substantial generalisation improvements towards unseen scenes …
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
