PixelScanner - Poser

Calibration is the process of finding the true parameters of a camera that produces a certain given image. Our solution to this problem is the PixelScanner-Poser. By using image information alone, it finds both the extrinsic and intrinsic parameters and outputs a sparse model of the scene, automatically.

For more information check out the PixelScanner page.

PixelScanner - Cloud

A point cloud model is a set of vertices in 3D space representing an object. It is the most basic form for model representation and they are most often created by 3D laser scanners. Our PixelScanner-Cloud software emulates this process by only making use of the captured images and generates a very dense oriented point cloud model without using any active device.

For more information check out the PixelScanner page.

PixelScanner - Mesh

A triangle mesh model is a collection of vertices and triangle faces that defines an object in 3D computer graphics. It is the most commonly used model representation in games, animations and any application that makes use of 3D models. Our PixelScanner - Mesh software automatically generates high quality textured mesh models of objects from their extracted point cloud models to address this requirements.

For more information check out the PixelScanner page.

Low Resolution Stereo Estimator

Depth map is an image that encodes the information relating to the distances of the surfaces of scene objects from a viewpoint. LRSE, low resolution stereo estimator, is our near real-time low cost low power stereo solver low resolution images.

For more information check out the LowRes Stereo page.

Star Gazer

A star tracker is a celestial reference device that recognizes star patterns, such as constellations, and detects the location and orientation of the spacecraft.

Aurvis is developing the first national star tracker system to be deployed in the next Turkish Satellite in collaboration with TUBITAK Space Technologies Research Institute.


Ambient Occlusion

Ambient occlusion is a crude representation of the true global illumination that represents how exposed each point in a scene is to the ambient lighting.

We have implemented a method to extract the AO map from stacks of images lighted from different but unknown directions. This way it becomes possible to render more realistic looking 3D scanned objects in Computer Graphics applications.

For more information check out the Ambient Occlusion page.

Color Processing

We have developed a number of color related filters while providing solutions for some computer vision problems and developed some others just for fun. Here, we present some of the interesting ones, specifically, contrast enhancement, photography style transfer and image decolorization with contrast preservation.

For more information check out the Color Processing page.

Model Estimation and Data Fitting

Model estimation and data fitting problems arise in all sorts of computer vision related studies. Here, we show the results of some of the recent small projects we've delivered related with multiple model estimation with an unknown number of models and constrained least squares fitting results.

For more information check out the Model Fitting page.

Image Stitcher

Image stitching is the process of combining multiple images with overlapping fields of view to produce a panorama or a high resolution image. Our Stitcher software automatically calibrates images geometrically and photometrically and produces beautiful panoramas.

For more details, check out our Stitcher page.