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 …
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