This is the official repo for Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation (ICCV 23).
-
Updated
May 24, 2024 - Python
This is the official repo for Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation (ICCV 23).
tools for sparse human annotation of three-dimensional [neuroscience] datasets
We introduce SCOPE-Net, a symmetry-consistent, prompt-enhanced radial 2.5D segmentation framework using a novel radial slicing strategy and graph harmonic deformation to efficiently reconstruct 4D fetal heart meshes from sparse annotations.
GUI and CLI for nnU-Net and nnInteractive-powered annotation. Train, validate and apply nnU-Net on labelled images, or start from unlabelled ones: create labels with nnInteractive and scribbles, then train and improve the model in iterations.
To associate your repository with the sparse-annotations topic, visit your repo's landing page and select "manage topics."