Appearance and Movement

Retour à l'acceuil

Appearance and Movement

Bilan de 2011 à mi-2016 et prospective du thème Apparence et Mouvement

Objectives / Challenges

Permanent participants

• Un professeur : Jean-Michel Dischler
• Une chargée de recherche : Hyewon Seo
• Cinq maîtres de conférences : Rémi Allègre, Karim Chibout, Frédéric Cordier, Arash Habibi, Basile Sauvage
• Un ingénieur : Frédéric Larue

Autres participants

• Doctorants :

Publication

2-LCS13G. Luo, F. Cordier, H. Seo. Compression of 3D Animation Sequences by Temporal Segmentation, Computer Animation and Virtual Worlds, Wiley-Blackwell, Vol. 24(3-4):365--375, May 2013. 4-LCS14 G. Luo, F. Cordier, H. Seo. Similarity of Deforming Meshes Based on Spatio-temporal Segmentation, dans Eurographics Workshop on 3D Object Retrieval, pp. 77--84, B. Bustos, H. Tabia, J.-P. Vandeborre, and R. Veltkamp (Eds.), Strasbourg, France, March 2014. 4-LSC14 G. Luo, H. Seo, F. Cordier. Temporal Segmentation of Deforming Meshes, Computer Graphics International, Sydney, Australia, June 2014. 8-Luog14 G. Luo. Segmentation de Maillages Dynamiques et Son Application pour le Calcul de Similarité, 2014. 4-LLS15 G. Luo, G. Lei, H. Seo. Joint Entropy based Key-frame Extraction for 3D Animations, Computer Graphics International, Strasbourg, France, June 2015. 2-LCS16 G. Luo, F. Cordier, H. Seo. Spatio-temporal Segmentation for the Similarity Measurement of Deforming Meshes, Visual Computer, Springer Verlag, Vol. 32(2):243-256, February 2016.

Résultats

• Human modeling – shape, movement, and perception

We have developed new techniques for analyzing time-varying shapes, such as similarity measurement, temporal- and spatial alignment, and correspondence computation. - Similarity metric of deforming meshes based on spatio-temporal segmentation 2 3 4. We have devised a similarity metric of deforming meshes based on a compact representation of the spatio-temporal segmentation, i.e. evolving graph. Our experiential results on a number of deforming meshes show that the motion similarities exhibited by deforming meshes can be captured correctly, despite their shape differences. - Temporal alignment of deforming meshes2 4. One important by-product of our similarity measurement between deforming meshes is their temporal alignment, i.e. optimal alignment of graphs (or the corresponding key frames). The alignment results between deforming meshes with similar motions show that the key frames performing similar actions are matched well to each other. - Dynamic feature point detector/descriptor 5 6. To the best of our knowledge, our work is the first that addresses the spatio-temporal feature detector in animated meshes. Apart from guiding the registration of deforming meshes in our work, the results of our feature detection algorithm can be used in a number of promising applications, such as animation temporal alignment, animated mesh simplification, viewpoint selection etc. - Global correspondence optimization7. We have developed a new technique for registration of dynamic meshes based on the deformation feature descriptor and the optimization in spherical embedding. Spherical parameterization aids to reduce significantly the number of degrees of freedom in the numerical optimization, and thus computational cost.

• Acquisition de l'apparence

• Modélisation et synthèse de textures

Perspectives