Z
Zijian Zhu
Researcher at Institute for Infocomm Research Singapore
Publications - 33
Citations - 703
Zijian Zhu is an academic researcher from Institute for Infocomm Research Singapore. The author has contributed to research in topics: Pixel & Image processing. The author has an hindex of 10, co-authored 26 publications receiving 548 citations. Previous affiliations of Zijian Zhu include Agency for Science, Technology and Research.
Papers
More filters
Journal ArticleDOI
Weighted guided image filtering.
TL;DR: Experimental results show that the resultant algorithms produce images with better visual quality and at the same time halo artifacts can be reduced/avoided from appearing in the final images with negligible increment on running times.
Journal ArticleDOI
Hybrid Patching for a Sequence of Differently Exposed Images With Moving Objects
TL;DR: This paper proposes a hybrid patching scheme composed of a correction method which is an intensity mapping function at pixel level, and a hole-filling method that uses block-level template matching that is able to prevent ghosting artifacts from appearing in the final synthesized HDR image.
Proceedings ArticleDOI
Movement detection for the synthesis of high dynamic range images
TL;DR: An intensity mapping function (IMF) based scheme to detect moving objects in a set of low dynamic range images with different known exposure times to remove ghosting artifacts from the eventual high dynamic range (HDR) image is proposed.
Patent
Method and device for image processing
TL;DR: In this paper, a method for processing an input image having a plurality of pixels, wherein each pixel has a pixel position, is presented, where the method may include determining, for each pixel position a vector based on the input image; and determining a detail value for the pixel position based on determined vectors at a pluralityof neighboring pixel positions within a predetermined neighboring block of the pixel positions.
Journal ArticleDOI
Exposure-Robust Alignment of Differently Exposed Images
TL;DR: This letter presents a novel exposure-robust method to align differently exposed images that is less sensitive to the reference image, and robust to 12 exposure values (EV) increments, which is superior to existing methods.