Projects sharing features with Sam 3d Body

DensePose is a 3D human pose estimation framework designed to map 2D image pixels to a 3D surface-based model of the human body in real time. It functions as a computer vision anatomical mapper that projects 2D visual data onto a 3D surface to create detailed anatomical representations. The system operates as an image-to-3D texture transfer engine, localizing 2D image annotations onto 3D models to apply photographic textures to digital human representations. It uses a surface-based body mapping method to associate human pixels in an RGB image with specific coordinates on a 3D body template.

MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

DeepLabCut is a deep learning toolkit for markerless 2D and 3D animal pose estimation. It functions as a motion tracking system that identifies anatomical keypoints on animals in video sequences without the need for physical markers. The framework utilizes transfer learning and a library of pre-trained weights to accelerate the training of networks for different species. It supports multi-individual identity tracking to maintain unique identities across video sequences and offers real-time pose detection for live video feeds. The system covers a broad range of computer vision capabilities, i

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and tetrahedral meshes. It functions as an image-to-3D reconstructor and text-to-3D generator, utilizing a differentiable 3D renderer to produce realistic visual perspectives and material effects. The system enables the creation of 3D assets from single 2D images, point clouds, or descriptive text prompts. It features a latent space interpolator for creating smooth transitions between different 3D objects and supports the independent control of geometry and texture. The project cov

AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and tracking human body, face, hand, and foot keypoints in images and videos. It provides a system for skeletal posture estimation and multi-person pose tracking. The project implements tools for three-dimensional human pose reconstruction, generating joint positions and body mesh shapes from two-dimensional image data. It also includes a multi-person pose tracker capable of maintaining the identity of multiple people across consecutive video frames. The framework covers a broad

This project is a modular PyTorch framework for training and evaluating object detection and instance segmentation models. It serves as a computer vision research tool and a deep learning inference engine designed to identify object locations, classes, and pixel-level masks within images. The framework implements a two-stage inference pipeline that utilizes region proposal networks and a symmetric mask-head architecture. It provides specialized capabilities for instance segmentation, object bounding box detection, and human pose estimation via anatomical keypoint detection. The system includ

paper project page

First dataset of dressed humans with specific geometry representation for the clothes. It contains ~2 Million images with 40 male/40 female performing 70 actions. Every subject-action sequence is captured from 4 camera views and annotated with: RGB, 3D skeleton, body part and cloth segmentation…

Champ is a generative vision system and controllable image-to-video generator designed for human image animation. It uses a diffusion-based video synthesizer and 3D parametric guidance to transform a single reference image into a consistent sequence of motion based on external driving data. The framework distinguishes itself through a human pose transfer system that employs 3D body parametric extraction and coordinate-space alignment. This allows the model to map motion from a driving video to a reference person by adjusting for body scales and camera perspectives using depth and semantic con

PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

This is a multi-person pose estimation framework designed for real-time human keypoint detection. It functions as a bottom-up human pose estimator that identifies skeletal joints across all people in a scene without requiring a separate person detector. The system utilizes a convolutional neural network model to generate heatmaps and vector fields for posture analysis. It specifically implements part affinity fields to encode the location and orientation of limbs, allowing the model to connect individual joints into complete skeletons. The project covers computer vision motion analysis and d

This project is a deep learning framework built for detecting and tracking human body keypoints in images and video streams. It functions as both a real-time motion tracking system and a machine learning environment for training and evaluating pose estimation models. The system utilizes a two-branch convolutional neural network to predict body part locations and their directional connections simultaneously. It employs multi-stage feature refinement to improve keypoint localization accuracy and uses greedy parsing and bipartite matching algorithms to associate detected parts into individual sk

VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time. The project includes a semi-supervised learning pipeline that improves pose accuracy by combining labeled datasets with unlabeled video data and projection consistency loss. It also features a video pose visualizer capable of rendering 3D skeleton reconstructions and 2D keypoints as overlays on original footage. The framework covers the

OpenPose is a real-time pose estimation engine designed to detect and track human body, face, hand, and foot landmarks. It functions as a multi-person motion tracker, identifying the spatial coordinates of multiple individuals simultaneously within video streams or static images. Beyond two-dimensional detection, the software acts as a three-dimensional kinematics processor, reconstructing spatial movement data from single or multiple synchronized camera perspectives. The system distinguishes itself through a bottom-up approach that utilizes part-affinity fields to associate body parts across

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

Detectron2 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

GoCV is a computer vision library and Go language binding for OpenCV. It serves as an image processing toolkit and deep learning inference engine, providing programmatic access to a wide range of algorithms for image manipulation, object detection, and video analysis. The project differentiates itself through high-performance native bindings and hardware acceleration. It utilizes a foreign function interface to map Go calls to C++ functions and includes a hardware-agnostic backend dispatch to route neural network tasks to computation engines such as CUDA and OpenVINO. The library covers a br

RuView is a WiFi spatial sensing platform that uses radio frequency reflections to detect presence, track body poses, and monitor vital signs without the use of cameras. It functions as a 3D point-cloud spatial mapper, converting signal disturbances into coordinate sets to visualize physical environments and human movement. The system operates as a distributed sensing mesh where synchronized nodes use consensus and shared audit trails to maintain data consistency across a swarm. It further acts as an MQTT home automation bridge, streaming real-time spatial telemetry and occupancy data to smar

YOLOv7 is a PyTorch vision library and real-time inference engine designed for object detection, human pose estimation, and instance segmentation. It provides a framework for detecting and locating multiple objects within images or video streams using neural networks. The system includes tools for custom model training and fine-tuning, allowing pre-trained weights to be adapted to specialized datasets via transfer learning. It also supports model weight export and format conversion to facilitate deployment on production servers and embedded edge devices.

This project is a 3D visual localization framework designed to determine a camera's exact position and orientation by matching 2D image features against a 3D reference model. It includes a structure-from-motion pipeline to reconstruct 3D scene geometry from unordered image sets, creating the necessary spatial maps for localization. The system employs a hierarchical coarse-to-fine localization approach. This process begins with a global-descriptor image retrieval system to identify candidate reference images from a large database and progresses through local feature matching to final 3D model

TaskMatrix is a multimodal AI chat interface and visual task orchestrator. It combines language models with visual recognition to enable the exchange, analysis, and modification of images within a conversational environment. The system coordinates multiple foundation models through orchestration pipelines that chain language, detection, and segmentation models. This allows for complex visual operations, such as using text instructions to guide image masking and executing modular inpainting workflows to edit specific image regions. The project includes a computer vision toolset for object det

This project is a computer vision system for object segmentation and tracking across images and videos. It employs models capable of identifying and masking objects using text prompts, bounding boxes, click points, or image exemplars. The system differentiates itself through memory-based video tracking and shared-memory architectures that maintain consistent object identities over time. It supports multi-object processing in single computation passes to increase frame throughput and utilizes iterative refinement to correct segmentation boundaries through sequential prompts. The software also

Relativ is an open-source project for the development of custom virtual reality hardware, encompassing the mechanical design, electronics, and software interfaces required to build a headset from scratch. It provides the frameworks necessary for assembling devices using open-source electronics and firmware. The project integrates custom hardware with SteamVR through driver-based configurations, mapping device identifiers and display viewports to ensure rendered images align with physical secondary displays. It employs a combination of microcontroller-based inertial measurement unit polling fo

Grounded-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

Neural renderer is a differentiable rendering library for PyTorch that projects three-dimensional meshes into two-dimensional images while maintaining continuous mathematical gradients for backpropagation. The framework enables gradient-based inverse rendering, allowing optimization of input parameters such as camera pose, vertex positions, and texture maps by propagating pixel-level reconstruction errors backward to the source geometry. The architecture incorporates approximate rasterisation gradients that substitute discontinuous edge derivatives with heuristic approximations to facilitate