PETR
Position Embedding Framework
Develops a framework for multi-view 3D object detection and perception from camera images using position embedding transformation.
[ECCV2022] PETR: Position Embedding Transformation for Multi-View 3D Object Detection & [ICCV2023] PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
881 stars
15 watching
132 forks
Language: Python
last commit: over 1 year ago
Linked from 1 awesome list
3d-position-embeddingmulti-cameramulti-task-learningobject-detectionsegmentation
amrzv/awesome-colab-notebooksRelated projects:
| Repository | Description | Stars |
|---|---|---|
| megvii-research/tlc | Improves image restoration performance by converting global operations to local ones during inference | 231 |
 vita-epfl/monoloco | A software framework for 3D vision and computer vision tasks using deep learning and 2D keypoints. | 431 |
 gink03/alt-i2v | An implementation of a deep learning-based image representation learning approach using a modified fully connected layer and transfer learning from VGG16 | 34 |
 gamrix/cs231n_proj | This project focuses on manipulating 3D views using deep learning techniques. | 6 |
 plasticityai/magnitude | A fast and efficient utility package for utilizing vector embeddings in machine learning models | 1,635 |
 jshilong/gpt4roi | Training and deploying large language models on computer vision tasks using region-of-interest inputs | 517 |
 appinho/sarosperceptionkitti | ROS package for perception processing and evaluation in the KITTI Vision Benchmark Suite | 247 |
 icetttb/planetr3d | An implementation of a deep learning-based method for 3D plane recovery from images. | 94 |
 vmarsocci/3dcd | Automatically inferring 2D and 3D change detection maps from bitemporal optical images without relying on DSMs. | 29 |
 esri/pyprt | Python bindings for CityEngine's procedural runtime for generating 3D models | 64 |
 megviirobot/camlasercalibratool | Automates extrinsic calibration of cameras and 2D lasers in robotics using ROS | 662 |
 petworm/larvio | An implementation of a monocular visual inertial odometry algorithm based on Multi-State Constraint Kalman Filter for accurate and robust localization | 737 |
| vita-epfl/crowdnav | Develops robot navigation policies in crowded spaces using reinforcement learning and attention mechanisms. | 607 |
 lavi-lab/visual-table | A project that generates visual representations tailored for general visual reasoning, leveraging hierarchical scene descriptions and instance-level world knowledge. | 14 |
 yunishi3/3d-fcr-alphagan | This project aims to develop a generative model for 3D multi-object scenes using a novel network architecture inspired by auto-encoding and generative adversarial networks. | 103 |