Adrian Munteanu

Artificial Intelligence

Cognitive Science

Vision and image recognition

Director, Electronics and Informatics (ETRO) - VUB


Adrian Munteanu (M’07) is professor at the Electronics and Informatics (ETRO) department of the Vrije Universiteit Brussel (VUB), Belgium. He received the MSc degree in Electronics and Telecommunications from Politehnica University of Bucharest, Romania, in 1994, the MSc degree in Biomedical Engineering from University of Patras, Greece, in 1996, and the Doctorate degree in Applied Sciences (Summa Cum Laudae) from Vrije Universiteit Brussel, Belgium, in 2003. In the period 2004-2010 he was post-doctoral fellow with the Fund for Scientific Research – Flanders (FWO), Belgium, and since 2007, he is professor at VUB.

His research interests include image, video and 3D graphics compression, 3D video, deep-learning, distributed visual processing, error-resilient coding, and multimedia transmission over networks.

Adrian Munteanu is the author of more than 350 journal and conference publications, book chapters, and contributions to standards and holds 7 patents in image and video coding. He is the recipient of the 2004 BARCO-FWO prize for his PhD work, and of 13 other awards and scientific prizes at national and international conferences. Adrian Munteanu served as Associate Editor for IEEE Transactions on Multimedia and currently serves as Associate Editor for IEEE Transactions on Image Processing.

Prof. Adrian Munteanu and has more than 25 years expertise in the area of data compression. Research in this area seeded many innovations and delivered state-of-the-art contributions in the domains of wavelet-based scalable image and video coding, volumetric image coding, distributed video coding, and various error resilient coding based on scalable multiple description quantizers (patented ETRO technology) and scalable joint source-channel coding techniques. In the area of 3D graphics, VUB-ETRO brought novel concepts, such as scalable L-infinite coding of meshes, enabling accurate control of the coding error at vertex level, designed state-of-the-art texture compression technologies significantly outperforming the standard DXT family of texture codecs, has developed the MESHGRID coding technology, which is an MPEG-4 AFX-standard, and proposed novel scalable coding methods providing state-of-the-art results in compression of semi-regular and irregular meshes.

Current research activities in the group led by A. Munteanu focus on multi-view multimodal sensor processing with topics including camera calibration, depth estimation, color correction, view interpolation, light field processing, and deep learning techniques for image, video and 3D graphics processing.

In these areas, the group led by prof. Munteanu has developed state-of-the-art methods in color correction in multicamera systems, calibration of light field cameras, and proposed innovative deep learning algorithms yielding state-of-the-art results in lenslet image coding, depth estimation in light field cameras, view synthesis, lossless image compression, semantic segmentation, quality enhancement, Time-of-Flight denoising, and automatic extraction of biometrics from 3D scans.