Workshop on Learning and Inference Methods for High Performance Imaging

In conjunction with ACCV 2018

Perth Convention & Exhibition Centre, 3 December 2018

High performance imaging technology generates images with high spectral and spatial resolution, high dynamic range, and/or at high speed. Hyperspectral images contain tens or hundreds of contiguous wavelength indexed bands that are related to material information. High spatial resolution images provide fine details on target objects. High dynamic range images present a great range of luminance levels to capture vivid lights or shadows. High speed cameras offer high frame rate to record fast moving objects. Sometimes, high performance imaging can also be achieved by combing the output of a large number of imaging devices.

While high performance imaging has greatly expanded the sensing capability of cameras to capture scenes or phenomena that are beyond human vision, the processing, analysis and understanding of these imaging modalities are still challenging, with many unsolved problems. In particular, various types of high performance images have their unique properties, and can be very large in size and pose a high computational burden. The workshop is aimed at leveraging modern machine learning and pattern recognition techniques to perform image processing, enhancement, recognition and scene understanding using high performance imaging. It will also provide a forum to researchers in the area to present their work and a means to interact with other members of the community sharing similar interests. Thus, the workshop will bring together academics and industrial scientists working on machine learning for large camera arrays, high dynamic range, high speed, polarimetric, fluorescence, hyperspectral, multispectral and extreme imaging.


Invited Speakres Program


Antonio Robles-Kelly, Deakin University, Australia

Imari Sato, National Institute of Informatics, Japan

Mehrdad Shoeiby, CSIRO, Australia



The topics of interest, from the theory and practice point of view, include but are not limited to

With applications in

Submission Guidelines

All submissions will be handled electronically through the online submission system, whereby each paper will undergo double-blind reviewing according to ACCV guidelines. Moreover, in submitting a manuscript to this workshop, the authors acknowledge that no paper substantially similar in content has been submitted, published or accepted for publication at another workshop or conference.

Manuscripts should be submitted as PDF files and should be no more than 14 pages for content plus maximum 2 pages for references. The paper template is identical to the main ACCV2018 conference (LaTeX templates in ZIP format are available HERE). An example submission paper with detailed instructions is available HERE

Important dates