| Proj No. | A3220-251 |
| Title | Deep Learning for Generalized Image Restoration and Reconstuction |
| Summary | Despite of the recent advance in deep single image processing and analytics, it is still challenging to design deep multi-modality modeling methods to fully exploit the correlations amongst measurements from complementary modalities, thus the information can be jointly extracted for better analytics. Comparing to conventional approaches, deep methods introduce less bias on modality understanding, while having better flexibility to construct prior using data-driven approaches. In this project, we aim to investigate modern deep learning methods to reconstruct or analyze multi-modality data by exploiting their intra-modality properties, such as cross-channel and non-local correlation. Recent multi-modality neural networks will be studied and new methods will be investigated. Our team has recently proposed several state-of-the-art deep-learning methods for low-light image enhancement and shadow removal, which are published on top-tier conferences such as CVPR, ECCV, AAAI, etc. The qualified student candidate can work together with the senior researchers to further develop the baseline algorithms. Candidates need to have experience in deep learning and image processing. Interested candidates can email their CVs to me (bihan.wen@ntu.edu.sg). Only qualified candidates will be notified. |
| Supervisor | A/P Wen Bihan (Loc:S2 > S2 B2B > S2 B2B 54, Ext: +65 67904708) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Centre for Information Sciences & System (CISS) (Loc: S2-B4b-05) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |