There are 1 repository under scannet topic.
Pytorch framework for doing deep learning on point clouds.
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
[WACV2022] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection
[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation
[ECCV2022] FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs (CVPR 2023)
[ECCV'20] Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
[ICIP2023] TR3D: Towards Real-Time Indoor 3D Object Detection
[WACV'24] TD3D: Top-Down Beats Bottom-Up in 3D Instance Segmentation
This work is based on our paper "DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes", which appeared at the IEEE Conference On Computer Vision And Pattern Recognition (CVPR) 2020.
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
[CVPR 2023] Unsupervised Continual Semantic Adaptation through Neural Rendering
ENet for 2D semantic segmentation in ScanNet
Official implementation for the ECCV 2022 work MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud
PFA-ScanNet: Pyramidal Feature Aggregation With Synergistic Learning for Breast Cancer Metastasis Analysis (Architecture Only Pytorch Implementation).
Complete surface texture on partially textured 3D meshes using graph neural networks.
[CVPR2022] Point Cloud Pre-training with Natural 3D Structures
Tool that allows you to view the RGBD video of a ScanNet sens file
Senior Design project that presents scanned devices in your network in a user-friendly GUI