Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Learning Rigid Objects Dynamics from Videos
Understanding the dynamics of rigid object interactions is crucial in various fields, including robotics, computer graphics, and physics-based simulations. In this project, you will focus on the task of learning/simulating rigid objects dynamics from videos, with the end-goal of predicting future or alternative trajectories for the objects in the scene.
Keywords: Computer Vision, Mechanics, Scene Understanding, Object-centric Learning
In this project, you will focus on the task of learning/simulating rigid objects dynamics from videos, with the end-goal of predicting future or alternative trajectories for the objects in the scene.
This task includes the decomposition of a visual scene into multiple blocks (identifying individual objects), the modeling of their evolution and interactions in the scene (positions, velocities, collisions,...), and the prediction of future (or alternative) trajectories (also called rollout).
In this project, you will focus on the task of learning/simulating rigid objects dynamics from videos, with the end-goal of predicting future or alternative trajectories for the objects in the scene.
This task includes the decomposition of a visual scene into multiple blocks (identifying individual objects), the modeling of their evolution and interactions in the scene (positions, velocities, collisions,...), and the prediction of future (or alternative) trajectories (also called rollout).
The objectives of the project are:
- Understanding the core concepts of Scene-Understanding and Object-Centric Representations
- Identify the current state-of-the-art methods for learning/simulating rigid objects dynamics
- Reproducing a subset of the selected baseline methods on existing datasets
- If possible, extend the existing approaches by a method of your choice (e.g. embedding physical inductive biases in the architecture, improving the explainability, reducing the data or computational requirements, ...)
The objectives of the project are:
- Understanding the core concepts of Scene-Understanding and Object-Centric Representations
- Identify the current state-of-the-art methods for learning/simulating rigid objects dynamics
- Reproducing a subset of the selected baseline methods on existing datasets
- If possible, extend the existing approaches by a method of your choice (e.g. embedding physical inductive biases in the architecture, improving the explainability, reducing the data or computational requirements, ...)