Miao Wang  |  Postdoc    [Curriculum Vitae]

Tsinghua University       Xidian University





Address:  Room 3-524, FIT Building, Tsinghua University, Beijing, P.R. China. Postcode: 100084.





  • I started my postdoc research in CSCG group, Tsinghua University, Beijing, working with Prof. Shi-Min Hu.






    I am a post-doctoral researcher in Computer Science at Tsinghua University, Beijing, working with Prof. Shi-Min Hu.



    I received my bachelor's degree in Computer Science and Technology from Xidian University in 2011 and PhD degree from Tsinghua University in 2016, supervised by Professor Shi-Min Hu.



    My research interests are in computer graphics and computer vision, especially in image/video content understanding and content-aware image/video editing.





    Hyper-lapse from Multiple Videos


    Miao Wang, Jun-Bang Liang, Song-Hai Zhang, Shao-Ping Lu, Ariel Shamir and Shi-Min Hu.


    Technical Report, 2016.PROJECT   PAPER  VIDEO (coming soon)


    Hyper-lapse video at high speed-up rate is an efficient way to illustrate long videos such as a human activity in first-person view. Existing hyper-lapse video creation methods produce fast-forward video effect from only one video source. In this work, we present a novel hyper-lapse video creation approach from multiple videos. We assume the videos share a common view, location or subject, and find transition points where jumps from one video to another can occur. We represent the collection of videos using the hyper-lapse transition graph where edges between nodes represent possible hyper-lapse frame transitions. To create a hyper-lapse video, we run a shortest path search algorithm on the digraph that optimizes the frame sampling and assembly simultaneously. Finally, we render hyper-lapse results using video stabilization and appearance smoothing techniques on the selected frames. With the proposed technique, one can synthesize novel virtual hyper-lapse routes which may not exist originally. We show various application results on both indoor and outdoor video collections with static scenes, moving objects as well as crowds.



    Comfort-driven Disparity Adjustment for Stereoscopic Video


    Miao Wang, Xi-Jin Zhang, Jun-Bang Liang, Song-Hai Zhang and Ralph R. Martin.


    Computational Visual Media (CVM) 2016. PAPER   BibTeX


    Pixel disparity--the offset of corresponding pixels between left and right views--is a crucial parameter in stereoscopic three-dimensional (S3D) video, as it determines the depth perceived by the human visual system. Unsuitable pixel disparity distribution throughout an S3D video may lead to visual discomfort. We present a unified and extensible stereoscopic video disparity adjustment framework which improves the viewing experience for an S3D video: keep the perceived 3D appearance as unchanged as possible while minimizing discomfort. We first analyse disparity and motion attributes of S3D video in general, then derive a wide-ranging visual discomfort metric from existing perceptual comfort models. An objective function based on this metric is used as the basis of a hierarchical optimisation method to find a disparity mapping function for each input video frame. Warping-based disparity manipulation is then applied to the input video to generate the output video, using the desired disparity mappings as constraints. Our comfort metric takes into account disparity range, motion and stereoscopic window violation; the framework could easily be extended to introduce further visual comfort models. We demonstrate the power of our approach using both animated cartoon and real S3D videos.



    BiggerPicture: Data-Driven Image Extrapolation Using Graph Matching


    Miao Wang, Yu-Kun Lai, Yuan Liang, Ralph R. Martin and Shi-Min Hu.


    ACM Transactions on Graphics, 33(6), SIGGRAPH Asia 2014.   PROJECT PAGE


    Filling a small hole in an image with plausible content is well studied. Extrapolating an image to give a distinctly larger one is much more challenging--a significant amount of additional content is needed which matches the original image, especially near its boundaries. We propose a data-driven approach to this problem. Given a source image, and the amount and direction(s) in which it is to be extrapolated, our system determines visually consistent content for the extrapolated regions using library images. As well as considering low-level matching, we achieve consistency at a higher level by using graph proxies for regions of source and library images. Treating images as graphs allows us to find candidates for image extrapolation in a feasible time. Consistency of subgraphs in source and library images is used to find good candidates for the additional content; these are then further filtered. Region boundary curves are aligned to ensure consistency where image parts are joined using a photomontage method. We demonstrate the power of our method in image editing applications.



    PatchNet: A Patch-based Image Representation for Interactive Library-driven Image Editing


    Shi-Min Hu, Fang-Lue Zhang, Miao Wang, Ralph R. Martin and Jue Wang.


    ACM Transactions on Graphics, 32(6), SIGGRAPH Asia 2013.   PROJECT PAGE   PAPER  VIDEO  SLIDES   CODE   DATA


    We introduce PatchNets, a compact, hierarchical representation describing structural and appearance characteristics of image regions, for use in image editing. In a PatchNet, an image region with coherent appearance is summarized by a graph node, associated with a single representative patch, while geometric relationships between different regions are encoded by labelled graph edges giving contextual information. The hierarchical structure of a PatchNet allows a coarse-to-fine description of the image. We show how this PatchNet representation can be used as a basis for interactive, library-driven, image editing. The user draws rough sketches to quickly specify editing constraints for the target image. The system then automatically queries an image library to find semanticallycompatible candidate regions to meet the editing goal. Contextual image matching is performed using the PatchNet representation, allowing suitable regions to be found and applied in a few seconds, even from a library containing thousands of images.



    Aesthetic Image Enhancement by Dependence-Aware Object Re-Composition


    Fang-Lue Zhang, Miao Wang and Shi-Min Hu.


    IEEE Transactions on Multimedia, 2013, 15(7).   PAPER


    This paper proposes an image-enhancement method to optimize photograph composition by rearranging foreground objects in the photograph. To adjust objects' positions while keeping the original scene content, we first perform a novel structure dependence analysis on the image to obtain the dependencies between all background regions. To determine the optimal positions for foreground objects, we formulate an optimization problem based on widely used heuristics for aesthetically pleasing pictures. Semantic relations between foreground objects are also taken into account during optimization. The final output is produced by moving foreground objects, together with their dependent regions, to optimal positions. The results show that our approach can effectively optimize photographs with single or multiple foreground objects without compromising the original photograph content.



    Professional Activities


    Paper review:  Pacific Graphics 2015, Computation Visual Media 2013, 2015, 2016.


    Talks:  MSRA Ph.D. Forum 2015, Visual Computing Group of Cardiff University 11/2013.





    2010 - Ranked 36th in World Finals of the 34th ACM International Collegiate Programming Contest (ICPC), Harbin, China.


    2009 - Gold Medal in Asia Regional Contest of the 34th ACM International Collegiate Programming Contest (ICPC), Hefei, China.


    2009 - Silver Medal in Asia Regional Contest of the 34th ACM International Collegiate Programming Contest (ICPC), Shanghai, China.








    visits since Dec. 2015.

    All the digital papers and videos in this page are the authors' version for personal use only.