Filters








1,557 Hits in 2.7 sec

Geodesic image and video editing

Antonio Criminisi, Toby Sharp, Carsten Rother, Patrick P'erez
2010 ACM Transactions on Graphics  
Numerous results on a variety of image and video editing tasks further demonstrate the effectiveness of our method.  ...  This paper presents a new, unified technique to perform general edgesensitive editing operations on n-dimensional images and videos efficiently.  ...  and video editing tasks effectively.  ... 
doi:10.1145/1857907.1857910 fatcat:x4oxmtvt5zdn3n5gihygiaok2u

ColorBrush: Animated diffusion for intuitive colorization simulating water painting

Nicolas Marki, Oliver Wang, Markus Gross, Aljosa Smolic
2014 2014 IEEE International Conference on Image Processing (ICIP)  
Water painting is an art, where the result and experience strongly depend on the process of creating it. Color is injected by the artist in a controlled way and diffuses into a final state.  ...  The geodesic distance builds the mathematical foundation for our animated diffusion. We add a time-dependent weight function to generate a diffusion-like spreading effect.  ...  [10] , who present a general image editing framework that propagates sparse user input based on the geodesic distance. Sagiv et al.  ... 
doi:10.1109/icip.2014.7025943 dblp:conf/icip/MarkiWGS14 fatcat:3z5wdvlasze5hmwlb7cywfqd4i

Geodesic-based Salient Object Detection [article]

Richard M Jiang
2013 arXiv   pre-print
We also applied our geodesic cut scheme to a number of image editing tasks as demonstrated in additional experiments.  ...  Other than using various pixel-level contrast definitions, we exploited global image structures and proposed a new geodesic method dedicated for salient object detection.  ...  There are many leaps between sections and paragraphs and unexplained statements, making the paper hard to understand and evaluate the correctness of the proposed methods.  ... 
arXiv:1302.6557v2 fatcat:dw4h3rw3yvdy7jjurkxat6l3ve

Interactive reflection editing

Tobias Ritschel, Makoto Okabe, Thorsten Thormählen, Hans-Peter Seidel
2009 ACM SIGGRAPH Asia 2009 papers on - SIGGRAPH Asia '09  
The system introduces a taxonomy of reflection editing operations, using an intuitive user interface, that works directly on the reflecting surfaces with real-time visual feedback using a GPU.  ...  We presented a total of 9 videos showing a Buddha statue, where 8 videos contained differently edited reflections and 1 video showed the unedited reflections, to 20 subjects.  ...  Finally, we showed all 9 videos simultaneously and asked the subjects to compare the unedited with the edited versions.  ... 
doi:10.1145/1661412.1618475 fatcat:4fhmvc2chzfoznbj5aayprqzje

Interactive reflection editing

Tobias Ritschel, Makoto Okabe, Thorsten Thormählen, Hans-Peter Seidel
2009 ACM Transactions on Graphics  
The system introduces a taxonomy of reflection editing operations, using an intuitive user interface, that works directly on the reflecting surfaces with real-time visual feedback using a GPU.  ...  We presented a total of 9 videos showing a Buddha statue, where 8 videos contained differently edited reflections and 1 video showed the unedited reflections, to 20 subjects.  ...  Finally, we showed all 9 videos simultaneously and asked the subjects to compare the unedited with the edited versions.  ... 
doi:10.1145/1618452.1618475 fatcat:cebipxc54jbilfsflbysk3v2ce

Similarity-based surface modelling using geodesic fans

Steve Zelinka, Michael Garland
2004 ACM SIGGRAPH 2004 Sketches on - SIGGRAPH '04  
As geodesic fans offer a a structurally equivalent definition of neighbourhoods everywhere on a surface, they are amenable to standard acceleration techniques and are well-suited to extending image domain  ...  We show how geodesic fans offer fast approximate alignment and comparison of surface neighbourhoods using simple spoke reordering.  ...  Thus, self-similarity based image editing provides a very powerful, intuitive tool for quickly editing textures and photographs.  ... 
doi:10.1145/1186223.1186344 dblp:conf/siggraph/ZelinkaG04 fatcat:aq5tk4rlrrds5bwyg5edsccinu

Similarity-based surface modelling using geodesic fans

Steve Zelinka, Michael Garland
2004 Symposium on geometry processing : [proceedings]. Symposium on Geometry Processing  
As geodesic fans offer a a structurally equivalent definition of neighbourhoods everywhere on a surface, they are amenable to standard acceleration techniques and are well-suited to extending image domain  ...  We show how geodesic fans offer fast approximate alignment and comparison of surface neighbourhoods using simple spoke reordering.  ...  Thus, self-similarity based image editing provides a very powerful, intuitive tool for quickly editing textures and photographs.  ... 
doi:10.1145/1057432.1057460 fatcat:m54fqwvh55epvdvwcfsdrfzxxy

Similarity-Based Surface Modelling Using Geodesic Fans [article]

Steve Zelinka, Michael Garland
2004 Symposium on geometry processing : [proceedings]. Symposium on Geometry Processing  
As geodesic fans offer a a structurally equivalent definition of neighbourhoods everywhere on a surface, they are amenable to standard acceleration techniques and are well-suited to extending image domain  ...  We show how geodesic fans offer fast approximate alignment and comparison of surface neighbourhoods using simple spoke reordering.  ...  Thus, self-similarity based image editing provides a very powerful, intuitive tool for quickly editing textures and photographs.  ... 
doi:10.2312/sgp/sgp04/209-218 fatcat:lvnni6xoyvbezp6ooob22oxbty

Dynamic surface matching by geodesic mapping for 3D animation transfer

Tony Tung, Takashi Matsuyama
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
We propose to perform dense surface matching between 3D video frames using geodesic diffeomorphisms.  ...  Surfaces are captured from multi-view video data and represented by sequences of 3D manifold meshes in motion (3D videos).  ...  Acknowledgments This work was supported in part by the Japan Society for the Promotion of Science (JSPS No.20.08366), and JST-CREST project "Creation of Human-Harmonized Information Technology for Convivial  ... 
doi:10.1109/cvpr.2010.5539806 dblp:conf/cvpr/TungM10 fatcat:zddkfftz6ncuxoiecsu5kyjhqi

Modeling and Compressing 3-D Facial Expressions Using Geometry Videos

Jiazhi Xia, Dao Thi Phuong Quynh, Ying He, Xiaoming Chen, Steven C. H. Hoi
2012 IEEE transactions on circuits and systems for video technology (Print)  
In this paper, we present a set of algorithms to construct geometry videos for 3D facial expressions, including hole filling, geodesic-based face segmentation, and expression-invariant parametrization.  ...  Geometry video naturally bridges the 3D motion data and 2D video, and provides a way to borrow the well-studied video processing techniques to motion data processing.  ...  Geometry images and videos The concept of geometry images was pioneered by Gu et al [6] , who parameterized the 3D mesh into a square domain and then encoded the normalized vertex coordinates (x, y, z  ... 
doi:10.1109/tcsvt.2011.2158337 fatcat:irymxzmtzrci7ep2jgzxxjoarm

Geodesic Video Stabilization in Transformation Space

Lei Zhang, Xiao-Quan Chen, Xin-Yi Kong, Hua Huang
2017 IEEE Transactions on Image Processing  
The experiments demonstrate the efficiency and effectiveness of our algorithm on stabilizing a variety of shaky videos.  ...  Specially, by using the geodesic solution in the space of rigid transformations, our approach even gains speedup 10× faster than state-of-the-art methods for path smoothing and motion compensation, and  ...  They are also grateful to Shuai-Cheng Liu and Fang-Lue Zhang for providing their results in the experiments.  ... 
doi:10.1109/tip.2017.2676354 pmid:28278466 fatcat:3clb4yn4cvaxhl5d3it6sjdfna

Automatic 3D Facial Expression Analysis in Videos [chapter]

Ya Chang, Marcelo Vieira, Matthew Turk, Luiz Velho
2005 Lecture Notes in Computer Science  
We introduce a novel framework for automatic 3D facial expression analysis in videos. The preliminary results were demonstrated by editing the facial expression with facial recognition.  ...  The real-time 3D video data were captured by a camera/projector scanning system. From this database, we extract the geometry deformation independent of pose and illumination changes.  ...  The second and the third images are the corresponding synthesized faces by the deformed dense mesh. , where n is the number of vertices; s is the number of videos and k is the length of the video.  ... 
doi:10.1007/11564386_23 fatcat:ikvnrggpdjggne3y66elqllit4

Temporally coherent 4D reconstruction of complex dynamic scenes [article]

Armin Mustafa, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2016 arXiv   pre-print
Robust joint segmentation and reconstruction of dynamic objects is achieved by introducing a geodesic star convexity constraint.  ...  Comparative evaluation is performed on a variety of unstructured indoor and outdoor dynamic scenes with hand-held cameras and multiple people.  ...  p and L (Γ) is the length of discrete geodesic path geodesic forest automatically.  ... 
arXiv:1603.03381v2 fatcat:hvo5vh55arbz3iaqrij7fvvslu

3D Face Apperance Model

B. Lading, R. Larsen, K. Astrom
2006 Proceedings of the 7th Nordic Signal Processing Symposium - NORSIG 2006  
We build a 3dface shape model, including inter-and intrashape variations, derive the analyticaljacobian ofits resulting 2d rendered image, and show example of its fitting performance with light, pose,  ...  id, expression and texture variations.  ...  Poggio and T. Vetter, Reanimating faces in Images and Video. Eurographics, vol 22, no. 3, 2003. ing shapes; b =[4T4] 14bT(x xo), and closest surface point registration is carried out.  ... 
doi:10.1109/norsig.2006.275249 fatcat:w42bjue5ibbxfegpceqb2vviyq

Front Matter: Volume 9399

2015 Image Processing: Algorithms and Systems XIII  
SPIE Image Processing: Algorithms and Systems XIII, edited by Karen O. Egiazarian, Sos S. Agaian, Atanas P.  ...  Utilization of CIDs allows articles to be fully citable as soon as they are published online, and connects the same identifier to all online, print, and electronic versions of the publication.  ...  -44] s), "Title of Paper," in Image Processing: Algorithms and Systems XIII, edited by Karen O.  ... 
doi:10.1117/12.2193222 fatcat:7cpxhoniqfcc3fioa5jfthht3i
« Previous Showing results 1 — 15 out of 1,557 results