Search Results for "3d capture"
Sort By:
Showing 68 open source projects for "3d capture"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
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.
-
1
The FreeMoCap Project
Free Motion Capture for Everyone
FreeMoCap is an open-source markerless motion capture system that enables users to record human movement using ordinary cameras and convert the footage into usable 3D motion data. The project’s goal is to democratize motion capture by removing the need for expensive suits or proprietary studio hardware, instead relying on computer vision and pose estimation pipelines. It processes synchronized video feeds to reconstruct skeletal motion, which can then be exported for animation, biomechanics research, or creative projects. ... -
2
HunyuanWorld-Mirror
Fast and Universal 3D reconstruction model for versatile tasks
HunyuanWorld-Mirror focuses on fast, universal 3D reconstruction that can ingest varied inputs and produce multiple kinds of 3D outputs. The model accepts combinations of images, camera intrinsics and poses, or even depth cues, then reconstructs consistent 3D geometry suitable for downstream rendering or editing. The pipeline emphasizes both speed and flexibility so creators can go from casual captures to assets without elaborate capture rigs. -
3
comfyui-mixlab-nodes
Workflow and speech recognition app
comfyui-mixlab-nodes is a large collection of custom nodes for ComfyUI that turns workflows into interactive apps and adds real-time multimedia, LLM, and TTS capabilities. It introduces a “Workflow-to-APP” concept, where a ComfyUI graph can be transformed into a Web App through an AppInfo node, complete with categories, batch prompts, and editable configurations. The project also brings Real-time Design features like screen capture and floating video nodes, enabling creative pipelines that... -
4
miniaudio
Audio playback and capture library written in C,
miniaudio is written in C with no dependencies except the standard library and should compile cleanly on all major compilers without the need to install any additional development packages. All major desktop and mobile platforms are supported. miniaudio gives you complete flexibility. With the low-level API, just initialize a connection to the device and send or receive raw audio data. The modular design of miniaudio allows you to use the low-level API without compromising your ability to... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Rivatuner
rivatuner statistics server
Introduced as a highly successful design with the help of a statistics server, these applications are designed to bring you the maximum functionality of your graphics card and bring you a bunch of controls that will help you get the most out of your GPU. can be specified. RivaTuner Download also lets you open-source overclocking and hardware debugging for NVIDIA video cards by modifying the NVIDIA graphics card, a revolutionary graphics card overclocking, and subsequent utility... -
6
KiCad EDA
A Cross Platform and Open Source Electronics Design Automation Suite
-
7
Odamex
Odamex is a free, cross-platform, modern client-server Doom engine
Odamex is a free, cross-platform (Mac, Windows, Linux) modification of the Doom engine that allows players to easily join servers dedicated to playing Doom online. The goal of Odamex is to add enhancements to Doom while still retaining that "classic Doom feel" we all know and love about the original game. -
8
ChaosEsqueAnthology
A free 3d game for PC that does not limit the player. Fight,Build,Gain
(NOTE: Make sure to download Volume2 aswell!: http://sourceforge.net/p/chaosesqueanthologyvolume2/ ) 200+ weapons. Build-able enter-able buildings (Like an FPS RPG but with interiors) (Multi-tool/ Utili-tool). City generation (all buildings enterable). A 2 iso (6GB) exploration of what QuakeC can do. Over 100 maps included, along with map editor and sourcecode. Fully free and opensource: code and media. A modification of Xonotic which included extended weapons, maps, vehicles,... -
9
Soul of Sphere Platinum
Save the World of Altara in my first RPG in 2D!
Altara is under the menace of the general Sphax. An ancient sphere calls young & old folks of a village in this world. Gamna, Arasyb, Ulania, Uniar, Dorna, Xylvan must save the lands of the years 3700 A.C. With unique weapons, battle numerous ennemies, grab items, buy gems, potions & artifacts. Now at v29.37 with Xilvan Design Sprites Library! Newly added grass, trees, flowers, butterflies and mp3 musics. This game will enchant you. A RPG made since 1999-2004 by Hypersphere... -
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
10
PIFuHD
High-Resolution 3D Human Digitization from A Single Image
PIFuHD (Pixel-Aligned Implicit Function for 3D human reconstruction at high resolution) is a method and codebase to reconstruct high-fidelity 3D human meshes from a single image. It extends prior PIFu work by increasing resolution and detail, enabling fine geometry in cloth folds, hair, and subtle surface features. The method operates by learning an implicit occupancy / surface function conditioned on the image and camera projection; at inference time it queries dense points to reconstruct a mesh via marching cubes. ... -
11
OpenSource OpenGL Multiplayer Multiplatform Battle Zone capture the Flag. 3D first person tank game. Download the latest version at https://www.bzflag.org/downloads/ Development has moved to Github: https://github.com/BZFlag-Dev/bzflag (The SourceForge binary releases for Windows and macOS are very outdated. Please download the latest version from our website.)
-
12
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. -
13
Multi Remote Camera
Trigger multiple cameras connected to a private local WiFi network
The Multi Remote Camera app for Android devices, takes photos and videos when triggered remotely over a local WIFI network using broadcast messages. You can capture photos and videos nearly simultaneously on local network connected devices running this camera app. Depending on the type of local private network, the number of triggered devices can range from 1 to 253 or 4093 maximum. To use the app for remote trigger you must enable WIFI Remote Control in Settings. For security reasons... -
14
MeshCNN in PyTorch
Convolutional Neural Network for 3D meshes in PyTorch
MeshCNN is a deep learning framework designed specifically for processing 3D triangular mesh data using convolutional neural networks. Unlike traditional CNNs that operate on images or voxel grids, MeshCNN performs convolution operations directly on the edges of mesh structures. This design allows the model to capture geometric relationships between mesh elements while preserving the underlying topology of 3D shapes. -
15
DensePose
A real-time approach for mapping all human pixels of 2D RGB images
...DensePose is widely used in augmented reality, motion capture, virtual try-on, and visual effects applications because it enables real-time 3D human mapping from 2D inputs. The model architecture builds on Mask R-CNN, using additional regression heads to predict UV coordinates that map image pixels to 3D surfaces. -
16
VideoPose3D
Efficient 3D human pose estimation in video using 2D keypoint
VideoPose3D is a deep learning framework that reconstructs 3D human poses from 2D keypoint sequences extracted from videos. It builds on top of convolutional and temporal networks that map 2D joint coordinates over time to consistent 3D skeletons, enabling robust motion capture without specialized sensors. The model is trained on large motion capture datasets and can generalize well to unseen environments by leveraging temporal context for smoothing and error correction. ... -
17
MatCaps
Huge library of matcap PNG textures organized by color
Matcaps is a comprehensive library of matcap (material capture) PNG textures organized by color, providing artists and developers with a wide range of materials for 3D modeling and rendering. Matcaps simplifies the process of applying consistent and realistic materials to 3D models, enhancing visual quality without the need for complex shader setups. -
18
NativeScript Augmented Reality
Augmented Reality NativeScript plugin
The nativescript-ar plugin brings augmented reality capabilities to NativeScript applications, allowing developers to create immersive AR experiences by integrating 3D objects and animations into the real world. -
19
I3D models trained on Kinetics
Convolutional neural network model for video classification
Kinetics-I3D, developed by Google DeepMind, provides trained models and implementation code for the Inflated 3D ConvNet (I3D) architecture introduced in the paper “Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset” (CVPR 2017). The I3D model extends the 2D convolutional structure of Inception-v1 into 3D, allowing it to capture spatial and temporal information from videos for action recognition. This repository includes pretrained I3D models on the Kinetics dataset, with both RGB and optical flow input streams. ... -
20
GazeRecorder
WebCam Eye Tracking for usability testing
WebCam Eye-Tracker. GazeRecorder automatically records using ordinary webcams, where people look and what they engage with on their computer screens. In comparison with conventional eye tracking - that uses specialized technology and invites respondents to labs – GazeRecoreder is able to track people’s eyes with their own computers at home. Multiple state-of-the-art tracking algorithms communicate to identify the face, key features, eyes, iris and movements in 3D, allowing for the... -
21
OncoBase
A platform for decoding regulatory somatic mutations in human cancers
...The vast majority of identified somatic mutations are located outside of coding sequences, making it challenging to directly interpret their functional effects. With the rapid advances in high-throughput chromosome conformation capture (3C)-based technologies, genome-scale long-range chromatin interactions were detected, and distal target genes of regulatory elements were determined using three-dimensional (3D) chromatin looping. Herein, we present OncoBase (http://www.oncobase.biols.ac.cn), an integrated database for annotating regulatory noncoding somatic mutations in human cancers by exploring their roles in distal interactions between target genes and regulatory elements. ... -
22
SIVIC is an open-source, standards-based software framework and application suite for processing and visualization of DICOM MR Spectroscopy data. Through the use of DICOM, SIVIC aims to facilitate the application of MRS in medical imaging studies.
-
23
xeogl
A WebGL-based 3D engine for technical visualization
...Camera animations (flyto, follow, path etc). Emphasis effects (wireframe, ghost, highlight, outline). Annotations. Cross-section views. Scene object hierarchies. Transform hierarchies. Bounding volumes. 3D picking, raycasting. Screen capture. You can dynamically edit most things in your scene at runtime. Animate your scenes by updating the properties of their components. Load 3D models into your scene from glTF. -
24
VideoMan Library
C++ library for image acquisition and visualization
Library for capturing video from cameras, 3d sensors, frame-grabbers, video files and image sequences. It can also display multiple images using OpenGL with different layouts. Easy integration with OpenCV, CUDA... Perfect for computer vision. Keywords: video capture, computer vision, machine vision, opencv, opengl, cameras, video input devices, firewire, usb, gige -
25
GLFFmpeg uses the video recording functionality provided by the FFmpeg library to capture content generated using OpenGL. The cross-platform library provides a minimalistic set of API to simplify the task of capturing OpenGL output to a video stream. GNU Lesser General Public License version 2.1 (LGPLv2.1)
