Search Results for "sam 3d body"
Sort By:
Showing 60 open source projects for "sam 3d body"
View related business solutions-
Gen AI apps are built with MongoDB AtlasMongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
-
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
1
SAM 3D Body
Code for running inference with the SAM 3D Body Model 3DB
SAM 3D Body is a promptable model for single-image full-body 3D human mesh recovery, designed to estimate detailed human pose and shape from just one RGB image. It reconstructs the full body, including feet and hands, using the Momentum Human Rig (MHR), a parametric mesh representation that decouples skeletal structure from surface shape for more accurate and interpretable results. -
2
SAM 3D Objects
Models for object and human mesh reconstruction
SAM 3D Objects is a foundation model that reconstructs full 3D geometry, texture, and spatial layout of objects and scenes from a single image. Given one RGB image and object masks (for example, from the Segment Anything family), it can generate a textured 3D mesh for each object, including pose and approximate scene layout. The model is specifically designed to be robust in real-world images with clutter, occlusions, small objects, and unusual viewpoints, where many earlier 3D-from-image systems struggle. ... -
3
MediaPipe
Cross-platform, customizable ML solutions for live and streaming media
MediaPipe offers open-source cross-platform, customizable ML solutions for live and streaming media. Provides segmentation masks for prominent humans in the scene. MediaPipe Face Mesh is a face geometry solution that estimates 468 3D face landmarks in real-time even on mobile devices. It employs machine learning (ML) to infer the 3D surface geometry, requiring only a single camera input without the need for a dedicated depth sensor. Utilizing lightweight model architectures together with GPU acceleration throughout the pipeline, the solution delivers real-time performance-critical for live experiences. ... -
4
PlayCanvas Engine
Fast and lightweight JavaScript game engine built on WebGL and glTF
PlayCanvas is an open-source game engine. It uses HTML5 and WebGL to run games and other interactive 3D content in any mobile or desktop browser. PlayCanvas is used by leading companies in video games, advertising and visualization such as Animech, Arm, BMW, Disney, Facebook, Famobi, Funday Factory, IGT, King, Miniclip, Leapfrog, Mojiworks, Mozilla, Nickelodeon, Nordeus, NOWWA, PikPok, PlaySide Studios, Polaris, Product Madness, Samsung, Snap, Spry Fox, Zeptolab, Zynga. The PlayCanvas Engine... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
HomeRobot
Mobile manipulation research tools for roboticists
...HomeRobot integrates perception, planning, and control under a unified architecture, supporting AI Habitat for simulation and ROS Noetic for real-world deployment. It provides interfaces for Detic, Grounded-SAM, and Contact-GraspNet, allowing open-vocabulary detection and 3D grasping. -
6
LÖVR
Lua Virtual Reality engine
An open-source framework for rapidly building immersive 3D experiences. You can use LÖVR to easily create VR experiences without much setup or programming experience. The framework is tiny, fast, open-source, and supports lots of different platforms and devices. Runs on Windows, Mac, Linux, Android, WebXR. Supports Vive/Index, Oculus Rift/Quest, Pico, Windows MR, and has a VR simulator. Simple VR scenes can be created in just a few lines of Lua. Writen in C99 and scripted with LuaJIT,... -
7
Watchy
An open source E-ink smartwatch
Watchy, an open-source E-Ink smartwatch. Watchy is an E-Paper watch with open-source hardware and software. It has a barebones design utilizing the PCB as the watch body, allowing it to be worn as-is, or further customized with different 3D printed cases and watch straps. It is a unique timepiece that is also a wearable development platform, allowing users to create their own experience. Ultra-low-power e-paper 1.54″ display with 200 x 200 resolution and wide viewing angle. Wi-Fi & Bluetooth LE connectivity. 3-axis accelerometer with gesture detection. ... -
8
DeepLabCut
Implementation of DeepLabCut
DeepLabCut™ is an efficient method for 2D and 3D markerless pose estimation based on transfer learning with deep neural networks that achieves excellent results (i.e. you can match human labeling accuracy) with minimal training data (typically 50-200 frames). We demonstrate the versatility of this framework by tracking various body parts in multiple species across a broad collection of behaviors. -
9
ElectronBot
ElectronBot is a mini desktop robot
ElectronBot is a desktop-scale robot platform designed for enthusiasts and makers, combining robotics, embedded systems, display, and gesture sensing into a compact mechanical “tool bot”. The project features six degrees of freedom (rotational axes) for arms, neck, and body, allowing expressive motion beyond simple head-tilt or arm-wave. It includes USB communication and a built-in display, enabling it to respond to host computer inputs and act as an interactive peripheral rather than just a static automaton. The creator provides full source materials—mechanical (3D printed or CNC parts), electronics (PCBs, custom boards), firmware and drivers—so someone can build or modify the robot themselves. ... -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
10
Amica
Amica is an open source interface for interactive communication
Amica is an open source interface for interacting with fully animated 3D characters that combine voice chat, vision, and an emotion engine into a single experience. It lets you hold natural conversations with AI characters that can see, listen, and speak, while expressing emotional states through facial expressions and body language. Users can import VRM character models, adjust their appearance, tune the voice to match the character, and define behavior using different large language models and TTS backends. ... -
11
PMViewer is a Visualization tool for Astrophysical N-Body and Hydro Simulations. GADGET-2 data support.With/Without periodical boundary conditions.Snapshot of scene in PPM and GIF formats.Flying in 3D space. Active/Passive Stereo 3D support.
-
12
A very simple java simulation of the human body to simulate a 3D drawing manikin,with plenty of freedom of movements of the limbs and rotation of the body to implements a 360 degrees view.Source code available.No openGL.Improvements to come !
-
13
ARHeadsetKit
Using $5 Google Cardboard to replicate Hololens
...Beyond that, AR has only played a minor role in the average person’s life, being used for a few occasional tasks such as measuring objects or testing out furniture. By interacting with detailed 3D models of the human body, surgeons can run through the steps of surgery and learn from mistakes in an environment that will not endanger a patient’s life. -
14
Monster Mash
New Sketch-Based Modeling and Animation Tool
...Under the hood it builds a lightweight surface and auto-assigns handles so you can grab and move parts intuitively, with smooth deformations propagating across the body. Because it runs interactively, artists iterate rapidly—blocking poses, trying alternate proportions, or recording short performances—before exporting results downstream. It’s equally useful for education, previs, and indie production where fast iteration trumps photorealism. -
15
FrankMocap
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
FrankMocap is a monocular 3D human capture system that estimates body, hand, and optionally face pose from a single RGB image or video. It regresses parametric human models (e.g., SMPL/SMPL-X) directly, producing temporally stable meshes and joint angles suitable for animation or analytics. The pipeline couples a robust 2D keypoint detector with 3D mesh regression networks and priors that keep results anatomically plausible. -
16
Twometer VR
Low budget open-source Virtual Reality controllers
TwometerVR is an open-source alternative to commercial VR hand/body tracking systems. It's primarily intended for those who have VR headsets such as the Oculus DK2 that don't include controllers. It is a low-cost alternative to expensive commercial devices such as the PS Move or Oculus Touch system. An open-source alternative to commercial hand trackers such as Oculus Touch or PS Move, because Virtual Reality should not be expensive. Although there is currently no implementation of... -
17
DensePose
A real-time approach for mapping all human pixels of 2D RGB images
DensePose is a computer vision system that maps all human pixels in an RGB image to the 3D surface of a human body model. It extends human pose estimation from predicting joint keypoints to providing dense correspondences between 2D images and a canonical 3D mesh (such as the SMPL model). This enables detailed understanding of human shape, motion, and surface appearance directly from images or videos. The repository includes the DensePose network architecture, training code, pretrained models, and dataset tools for annotation and visualization. ... -
18
OpenPose
Real-time multi-person keypoint detection library for body, face, etc.
OpenPose has represented the first real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images. It is authored by Ginés Hidalgo, Zhe Cao, Tomas Simon, Shih-En Wei, Yaadhav Raaj, Hanbyul Joo, and Yaser Sheikh. It is maintained by Ginés Hidalgo and Yaadhav Raaj. OpenPose would not be possible without the CMU Panoptic Studio dataset. We would also like to thank all the people who has helped OpenPose in any way. 15, 18 or... -
19
OFX extension for interactive stereo projection mapping (3D Workbench)
-
20
Rendertron
A Headless Chrome rendering solution
Rendertron is a headless Chrome rendering solution designed to render & serialise web pages on the fly. Rendertron is designed to enable your Progressive Web App (PWA) to serve the correct content to any bot that doesn't render or execute JavaScript. Rendertron runs as a standalone HTTP server. Rendertron renders requested pages using Headless Chrome, auto-detecting when your PWA has completed loading and serializes the response back to the original request. To use Rendertron, your... -
21
Relativty
An open source VR headset with SteamVR supports for $200
Relativty is not a consumer product. We made Relativty in my bedroom with a soldering iron and a 3D printer and we expect you to do the same, build it yourself. We started Relativty because after watching Sword Art Online we wanted to make our own VR games. Thus Relativty supports SteamVR games and can be modified to add support for any DIY or off-the-shelf VR device. The room-scaling AI can be used with any camera, it tracks your body based on video input. -
22
SmartBody
Character animation system for games and simulations.
SmartBody is available for download for Windows, Linux and OSX users. SmartBody can also be used on Android and iOS platforms. SmartBody is a character animation platform that provides the following capabilities in real time: * Locomotion (walk, jog, run, turn, strafe, jump, etc.) * Steering - avoiding obstacles and moving objects * Object manipulation - reach, grasp, touch , pick up objects * Lip Syncing - characters can speak with simultaneous lip-sync using text-to-speech or... -
23
perso3D chung is a simple 3D character model animation and easy editing program directly into openGL from a set of body parts 3ds files.Same animations data can be used for differents characters models. Multiple animations can occur at the same time. It is written in freebasic and uses gui_chung.. Lowcost,customizable and fast technique for freebasic programmers.
-
24
mini3d
3D Software Renderer in 700 Lines
The 3D software rendering tutorial, without any performance optimization, mainly shows people how to write a software renderer with a fixed pipeline. Although the main body code is only 700 lines, the sparrow is small and complete. The source code has only one mini3d.c, and a single file implements everything and is easy to read. No third-party library dependencies, no complicated project directories. -
25
PRINSOW
STL viewer for 3D printing
Free Open Source STL viewer (GNU GPL / No installation required) by El mehdi Abbou-ou-cherif. -------------------------------------------------------------------------- PRINSOW provides minimalistic but yet important features as given below. It is heavily based on VTK 6.1 and Qt 5.4.1 libraries. It is the first author contribution in the field of free software so any comment is welcomed. -------------------------------------------------------------------------- P.S. To use the...
