Vision & Learning
- Home
- CRL
- Embodied AI
- Vision & Learning
The Vision & Learning Group (VLG) focuses on learning from interaction in physical environments. Complex and safe manipulation and navigation technology leverage precise 3D geometry and scene understanding in conjunction with strong world-aware action selection frameworks. Learned concepts are effectively transfered to new domains.
Research
The VLG is conducting cutting edge research on a number of fields leading fundamental research to pioneer applications.
Resources
Driven by academic research results, the VLG contribution to the state-of-the-art methods in Perception, Reasoning, Action and Learning passes through shared resources to ensure reproducibility of results.
Selected publications
Modelling Partially Observable Systems using Graph-based Memory...
S. Morad, S. Liwicki, R. Kortvelesy, R. Mecca, A. Prorok
11/08/2021
LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
R. Mecca, F. Logothetis, I. Budvytis and R. Cipolla
17/11/2021
PX-NET: Simple, Efficient Pixel-Wise Training of Photometric Stereo Networks
18/10/2021
Vision & Learning Group Latest Publications
Information contained in news and other announcements is current on the date of posting, but subject to change without notice.
F Logothetis, I Budvytis, R Cipolla
WACV 2024
S Morad, R Kortvelesy, S Liwicki, A Prorok,
NeurIPS 2023
G Wu, C Zhang, S Liwicki,
BMVC 2023