Segment 3D object using 3D Gaussian Splatting with segmentation feature vector with Silva
Segment 3D object using 3D Gaussian Splatting with segmentation feature vector with Silva
Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation
arXiv paper abstract https://arxiv.org/abs/2404.12784
arXiv PDF paper https://arxiv.org/pdf/2404.12784.pdf
... introduce Contrastive Gaussian Clustering, a novel approach capable of provide segmentation masks from any viewpoint and of enabling 3D segmentation of the scene.
Recent works ... shown how to model the appearance of a scene via a cloud of 3D Gaussians, and how to generate ... images from a given viewpoint by projecting on it the Gaussians before α blending their color.
... train a model to include also a segmentation feature vector for each Gaussian.
... 3D scene segmentation, by clustering Gaussians according to their feature vectors; and to generate 2D segmentation masks, by projecting the Gaussians on a plane and α blending over their segmentation features.
Using ... contrastive learning and spatial regularization, ... method can be trained on inconsistent 2D segmentation masks, and still learn to generate segmentation masks consistent across all views.
... the resulting model is extremely accurate, improving the IoU accuracy of the predicted masks by +8% over the state of the art ...
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
Comments