Complex Object Correspondence Construction in Two-Dimensional Animation

Authors:
Jun Yu;Dongquan Liu;Dacheng Tao;Hock Soon Seah
Affiliations:
Department of Computer Science, Xiamen University, Xiamen, China;GameLab Annex II, School of Computer Engineering, Nanyang Technological University, Singapore,;Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia;GameLab Annex II, School of Computer Engineering, Nanyang Technological University, Singapore,
Venue:
IEEE Transactions on Image Processing
Year:
2011

Citing 0
Cited 21

Graph based transductive learning for cartoon correspondence construction

Neurocomputing
Human computer interactions for converting color images to gray

Neurocomputing
Interactive cartoon reusing by transfer learning

Signal Processing
Image classification by multimodal subspace learning

Pattern Recognition Letters
Semi-supervised distance metric learning based on local linear regression for data clustering

Neurocomputing
A multilevel structural technique for fingerprint representation and matching

Signal Processing
LF-EME: Local features with elastic manifold embedding for human action recognition

Neurocomputing
Joint geometry and variability for image recognition

Neurocomputing
Face identification using reference-based features with message passing model

Neurocomputing
Hypergraph-based multi-example ranking with sparse representation for transductive learning image retrieval

Neurocomputing
Transductive cartoon retrieval by multiple hypergraph learning

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
A comprehensive study on learning to rank for content-based image retrieval

Signal Processing
Cartoon features selection using Diffusion Score

Signal Processing
Rank canonical correlation analysis and its application in visual search reranking

Signal Processing
Correspondence construction for cartoon animation via sparse coding

Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Multi-view hypergraph learning by patch alignment framework

Neurocomputing
High-level attributes modeling for indoor scenes classification

Neurocomputing
Recognizing architecture styles by hierarchical sparse coding of blocklets

Information Sciences: an International Journal
Sparse Discriminative Information Preservation for Chinese character font categorization

Neurocomputing
Multiple spatial pooling for visual object recognition

Neurocomputing
Fuzzy deep belief networks for semi-supervised sentiment classification

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Correspondence construction of objects in key frames is the precondition for inbetweening and coloring in 2-D computer-assisted animation production. Since each frame of an animation consists of multiple layers, objects are complex in terms of shape and structure. Therefore, existing shape-matching algorithms specifically designed for simple structures such as a single closed contour cannot perform well on objects constructed by multiple contours with an open shape. This paper introduces a semisupervised patch alignment framework for complex object correspondence construction. In particular, the new framework constructs local patches for each point on an object and aligns these patches in a new feature space, in which correspondences between objects can be detected by the subsequent clustering. For local patch construction, pairwise constraints, which indicate the corresponding points (must link) or unfitting points (cannot link), are introduced by users to improve the performance of correspondence construction. This kind of input is convenient for animation software users via user-friendly interfaces. A dozen of experimental results on our cartoon data set that is built on industrial production suggest the effectiveness of the proposed framework for constructing correspondences of complex objects. As an extension of our framework, additional shape retrieval experiments on MPEG-7 data set show that its performance is comparable with that of a prominent algorithm published in T-PAMI 2009.