google-research-datasets / Objectron
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box descri…
☆2,235Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Objectron
- A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation …☆2,336Updated last month
- The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.☆1,279Updated last year
- Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding☆1,711Updated last month
- Dense Prediction Transformers☆2,022Updated 3 months ago
- The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detection on Point Clouds"☆1,245Updated 2 months ago
- gradslam is an open source differentiable dense SLAM library for PyTorch☆1,318Updated last year
- Atlas: End-to-End 3D Scene Reconstruction from Posed Images☆1,824Updated 2 years ago
- code for Mesh R-CNN, ICCV 2019☆1,139Updated 5 months ago
- A simple, fully convolutional model for real-time instance segmentation.☆5,025Updated last year
- OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT…☆3,554Updated last year
- Deep Hough Voting for 3D Object Detection in Point Clouds☆1,696Updated 2 years ago
- Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022☆936Updated last year
- A PyTorch Library for Accelerating 3D Deep Learning Research☆4,491Updated last week
- Geometric Computer Vision Library for Spatial AI☆9,950Updated this week
- Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Z…☆4,509Updated 2 months ago
- We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.☆1,627Updated last year
- Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"☆724Updated 7 months ago
- [IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking☆4,010Updated last year
- Visual localization made easy with hloc☆3,204Updated last week
- Simultaneous object detection and tracking using center points.☆2,384Updated 4 months ago
- TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow☆2,753Updated this week
- DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel …☆1,005Updated last year
- ☆1,487Updated 3 months ago
- An extension of Open3D to address 3D Machine Learning tasks☆1,855Updated last month
- Scaled-YOLOv4: Scaling Cross Stage Partial Network☆2,018Updated last week
- Plenoxels: Radiance Fields without Neural Networks☆2,828Updated last year
- (IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"☆1,678Updated 7 months ago
- OpenMMLab's next-generation platform for general 3D object detection.☆5,309Updated 4 months ago
- PyTorch3D is FAIR's library of reusable components for deep learning with 3D data☆8,791Updated last week
- OpenMMLab Computer Vision Foundation☆5,896Updated last week