Visual Computing & Artificial Intelligence Lab at TUM
None
Description:
The Visual Computing & Artificial Intelligence Lab at TUM is a group of research enthusiasts advancing cutting-edge research at the intersection of computer vision, computer graphics, and artificial intelligence. Our research mission is to obtain highly-realistic digital replica of the real world, which include representations of detailed 3D geometries, surface textures, and material definitions of both static and dynamic scene environments. In our research, we heavily build on advances in modern machine learning, and develop novel methods that enable us to learn strong priors to fuel 3D reconstruction techniques. Ultimately, we aim to obtain holographic representations that are visually indistinguishable from the real world, ideally captured from a simple webcam or mobile phone. We believe this is a critical component in facilitating immersive augmented and virtual reality applications, and will have a substantial positive impact in modern digital societies.
For Tasks:
For Jobs:
Features
- Real-time face tracking
- High accuracy tracking
- Photo-realistic re-rendering
- Modifications of a target video
- Change the expressions of a target video in real time
Advantages
- Highly-realistic digital replica of the real world
- Detailed 3D geometries, surface textures, and material definitions
- Strong priors to fuel 3D reconstruction techniques
- Holographic representations that are visually indistinguishable from the real world
- Immersive augmented and virtual reality applications
Disadvantages
- May require specialized hardware
- Can be computationally expensive
- May not be suitable for all applications
Frequently Asked Questions
Alternative AI tools for Visual Computing & Artificial Intelligence Lab at TUM
Similar sites
Experiments with Google
A collection of experiments that showcases the possibilities of building with TensorFlow Lite for Microcontrollers.
Adobe Labs
A place for us to share some of our explorations into the future of creativity, expression, and communication.
For similar tasks
Segment Anything
Segment Anything: The AI Model That Can Cut Out Any Object, in Any Image, With a Single Click
Holovolo
Immersive volumetric VR180 videos and photos, and 3D stable diffusion, for Quest and WebVR
For similar jobs
