Data-driven efficient production of cartoon character animation

Morishima, Shigeo; Kuriyama, Shigeru; Kawamoto, Satomi; Suzuki, Tomonari; Taira, Masaaki; Yotsukura, Tatsuo; Nakamura, Satoshi

doi:10.1145/1278780.1278872

Cited by 5 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the optimization technique, we use a maximization function Σ k−1 i D f i ,f i+1 with a constraint t(fi) < t(fi+1) where k denotes the number of keydata, fi denotes the i-th keydata, and t(fi) denotes the time when fi appears. In the figure, we can see that although [10] also obtains representative keydata, some of them are the same as other keydata, i.e. they have the same values.…”

Section: Comparisonmentioning

confidence: 98%

“…This method is then extended in [7] to accommodate their use of feature values from [11]. In contrast, [8] modeled the keypose extraction problem as a constrained matrix factorization problem and used an optimization technique to solve it, while [10] used an optimization technique to find a set of poses, in which the total distances of neighboring keyposes are maximized.…”

Section: Related Workmentioning

confidence: 99%

“…Our approach, although similar to [10], differs in that we focus on obtaining representative keyposes which are distinct, even if the motion is cyclic, e.g a running motion. The method proposed in this paper can be effectively used in such situations as described in [13].…”

Section: Related Workmentioning

confidence: 99%

“…dataset to illustrate the differences of our approach to the optimization technique described in [10] for the sake of clarity. As can be seen in Figure 3, this sine wave dataset is similar to mocap data in that it is continuous, it has both local and global maximum (minimum) points, and it may or may not be periodical depending on the interval.…”

Section: Comparisonmentioning

confidence: 99%

See 3 more Smart Citations

A Simple and Efficient Method to Extract Keyposes from Mocap Data

Tanuwijaya

Ohno

2010

The Journal of the Society for Art and Science

View full text Add to dashboard Cite

Researchers have been constantly developing new methods for generating realistic human motion. A common and popular approach is to use motion capture data or mocap data. However, this approach produces a mountain of data and there is an increasing necessity for quick and efficient mocap data search methods.For text documents, search results are usually returned in the form of a list of documents' titles. This allows users to quickly browse the search results and easily find the documents that they are looking for. Applying this method to mocap data requires the extraction of keyposes since displaying every frame will only present excessive and unnecessary information.The authors of this paper propose a simple and efficient method to automatically extract keyposes of mocap data. The proposed method requires only O(kn) operations. Thus, users can vary the search parameters and results will be presented interactively. Our results show that the proposed approach is applicable to mocap data of complex motions and motions composing of many motion segments.

show abstract

Section: Comparisonmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

A Simple and Efficient Method to Extract Keyposes from Mocap Data

Tanuwijaya

Ohno

2010

The Journal of the Society for Art and Science

View full text Add to dashboard Cite

show abstract

“…Several attempts have already been made in this direction. The MoCaToon project focused on key-frames for generating animation ( Morishima et al, 2007 ). Other projects have concentrated on editing, classifying, indexing, and compressing the motion capture data ( Tilmanne et al, 2009 ; Clifford and Baciu, 2005 ; Baak et al, 2008 ; Bulut and Capin, 2007 ).…”

Section: Introductionmentioning

confidence: 99%

An Efficient Method of Key-Frame Extraction Based on a Cluster Algorithm

Zhang

Zhou

et al. 2013

Journal of Human Kinetics

View full text Add to dashboard Cite

This paper proposes a novel method of key-frame extraction for use with motion capture data. This method is based on an unsupervised cluster algorithm. First, the motion sequence is clustered into two classes by the similarity distance of the adjacent frames so that the thresholds needed in the next step can be determined adaptively. Second, a dynamic cluster algorithm called ISODATA is used to cluster all the frames and the frames nearest to the center of each class are automatically extracted as key-frames of the sequence. Unlike many other clustering techniques, the present improved cluster algorithm can automatically address different motion types without any need for specified parameters from users. The proposed method is capable of summarizing motion capture data reliably and efficiently. The present work also provides a meaningful comparison between the results of the proposed key-frame extraction technique and other previous methods. These results are evaluated in terms of metrics that measure reconstructed motion and the mean absolute error value, which are derived from the reconstructed data and the original data.

show abstract