Markerless Motion and/or Pose and/or Face detection and/or tracking and it's 3D reconstruction (in real time)
Inspiration:
I get very interested when camera captured images and videos (or live videos) turn into 3D virtual characters and their motion into its animation. I want to pursue this feeling.
What is 3D reconstruction?. This link gives a basic foundational idea on 3D reconstruction from images. Using 3D reconstruction one can determine any object’s 3D profile, as well as knowing the 3D coordinate of any point on the profile. from section Motivation and applications from this link is euphoric. Plus the methods for 3D reconstruction and in detail explanation of Binocular stereo vision and how it works is beautiful. There are other sources and external link.
The Multi-View Environment, MVE, is an implementation of a complete end-to-end pipeline for image-based geometry reconstruction. It features Structure-from-Motion, Multi-View Stereo and Surface Reconstruction. MVE is written in C++ and comes with a set of efficient, cross-platform and easy-to-use libraries. The code runs on Linux, MacOS X and Windows.
A MUST HAVE COURSE ON MATHEMATICAL FOUNDATION FOR VISUAL COMPUTINGComputational Science and Engineering I, its video lectures collection are here. This course provides a review of linear algebra, including applications to networks, structures, and estimation, Lagrange multipliers. Also covered are: differential equations of equilibrium; Laplace's equation and potential flow; boundary-value problems; minimum principles and calculus of variations; Fourier series; discrete Fourier transform; convolution; and applications.
Associated is this book on Computer Vision for Visual Effects. The book describes classical computer vision algorithms used on a regular basis in Hollywood (such as blue-screen matting, structure from motion, optical flow, and feature tracking) and exciting recent developments that form the basis for future effects (such as natural image matting, multi-image compositing, image retargeting, and view synthesis).
Books and resources on Mathematics for Visual Computing (AI/ML/CV/CG):
Noteworthy open source libraries for visual computing:
CGAL is a software project that provides easy access to efficient and reliable geometric algorithms in the form of a C++ library. CGAL is used in various areas needing geometric computation, such as geographic information systems, computer aided design, molecular biology, medical imaging, computer graphics, and robotics.
The Visualization Toolkit (VTK) is an open-source, freely available software system for 3D computer graphics, modeling, image processing, volume rendering, scientific visualization, and 2D plotting. It supports a wide variety of visualization algorithms and advanced modeling techniques, and it takes advantage of both threaded and distributed memory parallel processing for speed and scalability, respectively.
The Point Cloud Library (or PCL) is a large scale, open project [1] for 2D/3D image and point cloud processing. The PCL framework contains numerous state-of-the art algorithms including filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation.
Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.
Althouh the libraries I mention in this point are far related to project topic, however they are noteworthy libraries under visual computing area :
The Geospatial Data Abstraction Library (GDAL) is a computer software library for reading and writing raster and vector geospatial data formats. Although it is used for GIS data I have put it here because it can come under visual computing with raster GIS data.
Another, library which uses GDAL is Orfeo Toolbox which also can fall under visual computing because it works on using maching learning and computer vision with GIS raster images.