Search Results for "human"

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. ...

AnimatedDrawings is a framework that converts user sketches or line drawings into fully animated 2D motion sequences using learned motion priors. The idea is that you draw a simple static figure (stick figure, silhouette, or contour lines), and the system produces plausible skeletal motion (walking, jumping, dancing) that adheres to the drawn shape constraints. The architecture separates shape embedding (to understand user-drawn geometry) from motion embedding / generation (to produce...

SteadyDancer is a research-oriented motion stabilization and dancer tracking system designed to analyze and correct motion in videos, making captured performances appear smoother and more stable while preserving expressiveness. It employs computer vision and motion modeling to estimate and reduce unwanted jitters, shakes, or camera wobbles — particularly in dance or movement sequences where traditional smoothing would distort intentional motion. By differentiating between intentional...

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.

...Perceptron * recursively transforms images and video streams in realtime and produces a combination of Julia fractals, IFS fractals, and chaotic patterns due to video feedback * evolves geometric patterns into the realm of infinite details and deepens the thought * records animations (movies) * saves and opens presets (state files) * loads user photographs or captures screen and webcam input * has user interface based on multiple mouse cursors, and almost the entire keyboard * has multiple windows and fullscreen mode * takes complex geometric transforms as input * applies numerous coloring techniques * smoothly transforms fractals and creates endless psychedelic journeys * resonates with the human perception Visit the Perceptron home page at http://perceptron.sourceforge.net

Vitral SDK (Vitral Software Development Kit) is a java based software architecture for the development of computer graphics applications. Supports solid modeling, offline and JOGL rendering, animation/simulation and human-machine interaction.

...Knotter aims to allow its user to design such patterns in an intuitive way and to provide easy ways to integrate the result in external general-purpose graphic software. For this purpose, designs created within Knotter can be save in a custom human-readable format and exported as Scalable Vector Graphics and in a wide number of raster image formats.

Gplot provides a convenient front-end for gnuplot. It accepts a large set of options to generate a single plot of one or more sets of data (overlaid as necessary).

The first 3d search engine for text. Javascript only. Work in all browsers. Ajax downloads new words (and links between them) as you move mouse to control AI to learn what you're looking for (in context) and put it on screen. Includes Wikipedia data

Pivot: Revolution is a remake of the highly popular Pivot Stickfigure Animator, which was designed to allow easy animation using stick figures. Pivot: Revolution, however, will add many features on top of it, allowing for further ease of use.

PerceptualDiff is an image comparison utility that compares two images using a perceptual metric. That is, it uses a computational model of the human visual system to determine if two images are visually different, so minor changes in pixels are ignored.

Terram is a fast-paced racing game through a randomly generated winding tunnel against computer or human opponents. Currently in early development.

Searches for font files, sorts them into folders by name and look and with human readable names, stores gathered font information in a database, can generate previews and posters, can find and remove duplicates and can reunite PostScript font families.

Orbis is a MMORPG engine, written in C++ and possibly Lua, that has IA agents and human inhabitants that interact. The world will totally changeable by the inhabitants.

Gold Section is a professional tool for making harmonious color palette. At first, such kind of color palette often required in Web pages/graphics design. Gold Section generated palette is an optimal for human perception.

Texco - the textualizer collection - is a program which converts files in binary format (typically images, sounds, 3d models, etc) to a textual description which is easy for a human to read, or to a computer to parse. Very old code (2003, 2004 or so?)

LainOS is an OpenSource project that seeks to revolutionize the the user experience by bridging the realm between \"Alien Elegance\" and Human Usability, and thus create a truly new and unique interface that is user savvy and beautiful.

Implementation of a Silhouette extraction algorithm [1]. Coded in octave (matlab). [1] M. Yamada, K. Ebihara, and J. Ohya. A New Robust Real-time Method for Extracting Human Silhouettes from Color Images. Int. Conf. on Auto. Face and Gesture Recog., 1998

Yet another human-readable plaintext music notation language. Somewhat similar to ABC and also Guido. Empty lines divide blocks of music, and every line is for one voice. Blocks can be repeated and merged to simplify structured composing.

This utility is created with the aim of accelerating development of Linux PSF2 (framebuffer) fonts. It does not work with X fonts. The program can "explode" existing PSF2 fonts, creating an human-readable graphical representation of each glyph which can then be re-compiled into a PSF2 font. The project supports the use of unicode tables at the end of fonts, but currently (Dec, 2012) not fully (sequences are not supported), but this should be simple to amend.