5 रिपॉजिटरी
Awesome GitHub Repositories3D
Locating and classifying objects within three-dimensional space using neural networks.
Distinct from Object Detection: Extends standard 2D object detection into 3D spatial coordinates.
Explore 5 awesome GitHub repositories matching artificial intelligence & ml · 3D. Refine with filters or upvote what's useful.
Awesome 3D GitHub Repositories
AI के साथ बेहतरीन रिपॉजिटरी खोजें।हम AI का उपयोग करके सबसे सटीक रिपॉजिटरी खोजेंगे।
- facebookresearch/detectron2
facebookresearch/detectron2
34,548GitHub पर देखेंDetectron2 is a PyTorch computer vision framework and visual recognition platform designed for training and deploying models for object detection, image segmentation, and visual recognition. It provides a research-oriented environment for training complex vision models with multi-GPU acceleration. The project includes a specialized object detection library for identifying and locating multiple objects via bounding boxes, as well as an image segmentation toolkit for creating pixel-level masks through instance, semantic, and panoptic segmentation. Additionally, it features a human pose estimati
Locates and classifies objects within three-dimensional space using fully convolutional networks.
Python - idea-research/grounded-segment-anything
IDEA-Research/Grounded-Segment-Anything
17,633GitHub पर देखेंGrounded-Segment-Anything is a suite of specialized tools for multimodal visual analysis, text-based segmentation, and generative image editing. It integrates text-to-bounding-box detection and high-precision image segmentation masks to function as a text-based image segmenter and an automated visual labeling tool. The project enables text-driven image editing by identifying objects through natural language to perform inpainting and element replacement. It further extends visual analysis into three dimensions, allowing for 3D human reconstruction and the generation of 3D bounding boxes from t
Extends two-dimensional segmentation masks into three-dimensional bounding boxes by projecting image coordinates.
Jupyter Notebook3d-whole-body-pose-estimationautomatic-labeling-systemcaption - xingyizhou/centernet
xingyizhou/CenterNet
7,565GitHub पर देखेंCenterNet is a center point object detection framework and real-time computer vision pipeline. It identifies objects and poses by predicting center points instead of using anchor boxes. The system functions as a 3D bounding box estimator, a human pose estimation model, and a tool for real-time object detection. It treats the placement of joints and object locations as center point detection problems to locate entities in images and three-dimensional space. Capabilities cover 3D object detection, human keypoint estimation, and live video analysis. The pipeline uses a single-stage feedforward
Locates and classifies objects within three-dimensional space using center point coordinates.
Python - francescopace/espectre
francescopace/espectre
6,472GitHub पर देखेंEspectre is an edge machine learning framework and motion detection platform that uses Wi-Fi Channel State Information to identify human presence and movement. It functions as a sensing toolkit for ESP32 microcontrollers, enabling the detection of motion through walls without the use of cameras or wearables. The project distinguishes itself by executing compact neural network classifiers and mathematical detection algorithms directly on the microcontroller. It utilizes a MicroPython runtime to allow for the prototyping and deployment of sensing logic and wireless signal processing algorithms
Estimates the 3D position of people or objects using an array of phase-coherent wireless nodes.
Pythoncsidiyesp-32 - fundamentalvision/bevformer
fundamentalvision/BEVFormer
4,519GitHub पर देखेंBEVFormer एक परसेप्शन फ्रेमवर्क है जो स्वायत्त ड्राइविंग के लिए मल्टी-कैमरा छवियों को बर्ड्स-आई-व्यू अभ्यावेदन (bird's-eye-view representations) में बदलता है। यह एक मल्टी-कैमरा विजन पाइपलाइन के रूप में कार्य करता है जो पर्यावरणीय समझ को सुविधाजनक बनाने के लिए कई कैमरा स्ट्रीम को एक एकीकृत स्थानिक परिप्रेक्ष्य में एकीकृत करता है। यह सिस्टम एक ट्रांसफार्मर-आधारित आर्किटेक्चर को लागू करता है जो स्थानिक छवि सुविधाओं और टेम्पोरल ऐतिहासिक डेटा को एकत्रित करने के लिए क्वेरी-आधारित फीचर निष्कर्षण और स्पैटियोटेम्पोरल नेटवर्क का उपयोग करता है। यह लगातार फ्रेम में दृश्य की एक स्थायी मेमोरी बनाए रखने के लिए आवर्तक टेम्पोरल संचय (recurrent temporal accumulation) का उपयोग करता है। यह फ्रेमवर्क 3D ऑब्जेक्ट डिटेक्शन और सिमेंटिक मैप सेगमेंटेशन के लिए क्षमताएं प्रदान करता है। यह त्रि-आयामी वस्तुओं की पहचान करने और पर्यावरणीय डेटा को सार्थक सिमेंटिक क्षेत्रों में विभाजित करने के लिए कन्वेन्शनल डिटेक्शन हेड के साथ मल्टी-व्यू इमेज फ्यूजन को जोड़ता है।
Locates and identifies three-dimensional objects in a scene by converting camera images into a bird's-eye-view perspective.
Pythonautonomous-drivingcomputer-visiondeep-learning
