Marcelo Bertalmío

Marcelo Bertalmío (Montevideo, 1972) received the B.Sc. and M.Sc. degrees in electrical engineering from the Universidad de la República, Uruguay, and the Ph.D. degree in electrical and computer engineering from the University of Minnesota in 2001. He is a Senior Research Scientist with the Spanish National Research Council (CSIC), and previously was Full Professor at University Pompeu Fabra, Spain. His current research interests are in developing more accurate vision models, with applications to imaging, vision science and computer vision. 

He is in Stanford’s list of the world’s top 2% scientists, ranked in the top 0.1% of his area. His publications total more than 15,000 citations. His paper “Image Inpainting” introduced the term “inpainting” into the image processing and computer graphics communities; the method was used by NASA to restore Venus images and included in one of chip-maker Intel’s image processing libraries. He was awarded the 2012 SIAG/IS Prize of the Society for Industrial and Applied Mathematics (SIAM) for co-authoring the most relevant image processing work published in the period 2008-2012. He has received the Femlab Prize, the Siemens Best Paper Award, the Ramón y Cajal Fellowship, and the ICREA Academia Award, among other honors. He was elected secretary of SIAM’s activity group on imaging and is a Senior Area Editor for IEEE Transactions in Image Processing.

Has obtained an ERC Starting Grant for his project “Image processing for enhanced cinematography” and two ERC Proof of Concept Grants to bring to market technologies for cinema postproduction. Since 2006 he has taken part in European research projects related to the film industry and has coordinated two H2020 projects, HDR4EU and SAUCE, involving world-leading companies in the field. Has an ongoing collaboration with NHK (Japan Broadcasting Corporation), the largest broadcasting company in the world alongside the BBC. Has co-authored 4 European patents and one Japanese patent.

Has written the books “Image Processing for Cinema” (CRC Press, 2014) and “Vision models for HDR and WCG imaging” (Elsevier, 2020), and edited the book “Denoising of Photographics Images and Video” (Springer, 2018). He presented tutorials on vision models for imaging and computer vision at CVPR 2020 and ICIP 2020.

He is the CSO and co-founder of the start-up Toneo, that provides software solutions for cinema postproduction.

Here’s the video of a talk at UCLA’s IPAM, with an overview of the research done at his lab in the period 2015-2020. More recently, he has introduced a novel formulation for the receptive fields of neurons that allows to develop more accurate and flexible models for visual perception and visual neuroscience, as well as to enhance the performance of image processing and computer vision methods.

Opportunity for postdocs: research project on a new machine learning framework based on vision and neuroscience, see here for details