facebookresearch / 3detrLinks
Code & Models for 3DETR - an End-to-end transformer model for 3D object detection
☆681Updated 2 years ago
Alternatives and similar repositories for 3detr
Users that are interested in 3detr are comparing it to the libraries listed below
Sorting:
- [CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling☆646Updated 7 months ago
- Group-Free 3D Object Detection via Transformers☆256Updated 4 years ago
- [NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies☆946Updated last year
- PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation☆435Updated last year
- [ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution☆614Updated last year
- Implementation of the Point Transformer layer, in Pytorch☆600Updated 3 years ago
- [NeurIPS'22] An official PyTorch implementation of PTv2.☆417Updated 2 years ago
- Stratified Transformer for 3D Point Cloud Segmentation (CVPR 2022)☆423Updated 2 years ago
- 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022)☆452Updated 2 years ago
- VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking (CVPR 2023)☆837Updated 2 years ago
- [ECCV2022] Masked Autoencoders for Point Cloud Self-supervised Learning☆584Updated 6 months ago
- Code for paper <PointContrast: Unsupervised Pretraining for 3D Point Cloud Understanding>☆348Updated 4 years ago
- Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)☆921Updated 2 years ago
- DepthContrast self-supervised learning for 3D☆273Updated 4 years ago
- [ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers☆768Updated last year
- This is an unofficial implementation of the Point Transformer paper.☆606Updated 3 years ago
- Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.☆670Updated last year
- Kernel Point Convolution implemented in PyTorch☆859Updated last week
- Repository of 3D Object Detection with Pointformer (CVPR2021)☆165Updated 2 years ago
- We extend Segment Anything to 3D perception by combining it with VoxelNeXt.☆561Updated 2 years ago
- Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)☆386Updated 2 years ago
- OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [PointNeXt](https://arxiv.…☆392Updated last year
- [NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models☆632Updated last year
- Official source code of Fast Point Transformer, CVPR 2022☆293Updated 2 years ago
- Code for CVPR 2021 oral paper "Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts"☆238Updated 3 years ago
- [NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning☆672Updated 3 years ago
- Point Transformers☆709Updated last year
- 4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)☆313Updated 2 years ago
- Official implementation of "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding" (CVPR, 2022)☆258Updated 2 years ago
- A list of 3D computer vision papers with Transformers☆449Updated last year