kumuji / volumentations
Augmentation package for 3d data based on albumentaitons
☆37Updated last month
Related projects: ⓘ
- ☆22Updated 4 years ago
- ☆52Updated 4 years ago
- 🔥Benchmarking Unsupervised Object Segmentation (NeurIPS 2022)☆33Updated last year
- [ICCV-23] Official implementation of SeedAL for seeding active learning for 3D semantic segmentation☆25Updated last year
- Implementation for paper "PointMixup: Augmentation for Point Cloud". Accepted to ECCV 2020 as spotlight presentation☆98Updated 3 years ago
- [ICCV, 2021] Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks https://arxiv.org/abs/2007.11679☆34Updated last year
- spatial transformer for 3d point clouds☆30Updated 2 years ago
- Public repository for paper "Finding Your (3D) Center: 3D object detection using a learned loss"☆16Updated last year
- Code release for CVPR 2021 paper "3D Spatial Recognition without Spatially Labeled 3D"☆27Updated 3 years ago
- ☆56Updated 10 months ago
- a Pytorch library for multi-view 3D understanding and generation☆80Updated last month
- Implementation of "Bidirectional Projection Network for Cross Dimension Scene Understanding" CVPR 2021 (Oral)☆169Updated 3 years ago
- Code for Spatial Semantic Embedding Network:Fast 3D Instance Segmentation with Deep Metric Learning☆42Updated 11 months ago
- [NeurIPS 2021] Official Matlab implementation of LOD: Large-Scale Unsupervised Object Discovery.☆20Updated 2 years ago
- [CVPR 2021] Forecasting the panoptic segmentation of future video frames☆47Updated 3 years ago
- Official Datasets and Implementation from our Paper "Video Class Agnostic Segmentation in Autonomous Driving".☆29Updated 3 weeks ago
- Implementation of ICCV2021(Oral) paper - VMNet: Voxel-Mesh Network for Geodesic-aware 3D Semantic Segmentation☆96Updated 2 years ago
- Official implementation of YOGO for point-cloud processing☆77Updated 3 years ago
- [ICCV'21] Pri3D: Can 3D Priors Help 2D Representation Learning?☆149Updated 2 years ago
- Semantic Scene Completion☆101Updated 4 years ago
- This is a C++ Inteface of MinkowskiNet☆14Updated 4 years ago
- ☆121Updated 10 months ago
- Code release for "From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks" (CVPR 2020)☆27Updated 4 years ago
- [Preprint 2022] “Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?” by Yi Wang, Zhiwen Fan, Tianlong Chen, Hehe Fan, Zh…☆61Updated last year
- SegGCN: Efficient 3D Point Cloud Segmentation with Fuzzy Spherical Kernel☆31Updated 4 years ago
- [ECCV 2022] Masked Discrimination for Self-Supervised Learning on Point Clouds☆91Updated 2 years ago
- ☆11Updated 2 years ago
- Learning with Noisy Labels for Robust Point Cloud Segmentation (ICCV2021 Oral)☆60Updated last year
- https://arxiv.org/abs/2104.02246 One Thing One Click (CVPR 2021) https://arxiv.org/abs/2303.14727 One Thing One Click++ (Arxiv)☆53Updated last year
- ☆41Updated 2 years ago
- [WACV 2023] A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation☆23Updated last year