PRIM Projects

Students carry out a research project of interesting research articles. The project will be supervised by one of our experts in the computer graphics field. In case of PRIM, it is also possible to carry out a project in a company, co-supervised by a teacher from our school, with a topic that has been validated by the teacher. (No PRIM project will be possible without the validation of the teacher).

The project will be evaluated by submitted work including a report and final defense. The report must be submitted by the student before the defense. The members of the Computer Graphics group may attend the defense and participate in the Q/A session. The evaluation criteria are not negotiable even in the topic from a company and even if there is confidential contents. If any constraints apply to the topic, the student must notify the host company and teacher before the project is accepted.

Topics

IMPORTANT: Please be aware of that the topics listed below will be flexibly adapted according to your background knowledge and interests. Moreover, in addition to the topics listed below, you can still discuss other topics with your potential supervisor. Please feel free to contact supervisors (listed at each topic below) if you have any interesting directions you want to investigate in the computer graphics area.

Differentiable Stable Fluid Solver using TensorFlow — Supervisor: Kiwon UM

This project aims to implement a stable fluid solver using machine learning library, TensorFlow, such that the solver is differentiable and can be integrated in training process. This topic requires good understanding of partial differential equations, in particular, the Navier-Stokes equations that model a variety of fluid flows. Moreover, it requires nice programming skills (particularly in Python). You should be able to make good use of TensorFlow.

Mesh Coloring — Supervisor: Amal Dev PARAKKAT

This project aims to build an interactive system to colour 3D meshes. Given a 3D mesh, the user/artist should be able to effortlessly color it using the tools developed during this project. The topic requires a good knowledge in programming, mesh manipulation libraries (for eg: libQGLViewer) and geometry packages (for eg: CGAL). Moreover, the project requires a good understanding of Geometry processing concepts.

Constrained Stipples from Images — Supervisor: Amal Dev PARAKKAT

This project starts with building a system that is capable of creating a constrained stippling of the given image. The system further will be used to develop interesting applications to give an NPAR feeling to various objects. The topic requires a good knowledge in programming, optimization, and geometry. Moreover, the project requires a basic understanding in image/video processing.

Extracting Smooth Surfaces from Voxels — Supervisor: Amal Dev PARAKKAT

The construction of a free-form 3D surface model is still dif icult. However, in our point of view, the construction of a simple voxel model is relatively easy because it can be built with blocks. Even small children can build a voxel model. In this project, we intend to develop a new method (using machine/deep learning) to convert a given voxel model into a smooth surface that matches human perception. The topic requires a good knowledge in programming, machine/deep learning, and geometry.

Interactive Animation Generation using Green's Function — Supervisor: Jiong CHEN

This project aims to implement an interactive system to generate or edit elastic deformation and dynamics using Green’s functions. The preliminary knowledge includes basic and simple notions of partial differential equations and their particular analytical solutions, i.e., Green’s function. Also, you should have basic skills of programming in C++ and using open-source GUI libraries, such as imgui.