Motion inpainting and extrapolation for special effect production
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Adaptive algorithms to track the PARAFAC decomposition of a third-order tensor
IEEE Transactions on Signal Processing
IEEE Transactions on Image Processing
Singular value decompositions and low rank approximations of tensors
IEEE Transactions on Signal Processing
Face recognition using a color PCA framework
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Dynamic texture synthesis using a spatial temporal descriptor
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Synthesis-in-the-loop for video texture coding
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Higher-order SVD analysis for crowd density estimation
Computer Vision and Image Understanding
A New Truncation Strategy for the Higher-Order Singular Value Decomposition
SIAM Journal on Scientific Computing
Dynamic texture synthesis in space with a spatio-temporal descriptor
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume Part I
Hi-index | 0.02 |
Videos representing flames, water, smoke, etc., are often defined as dynamic textures: "textures" because they are characterized by the redundant repetition of a pattern and "dynamic" because this repetition is also in time and not only in space. Dynamic textures have been modeled as linear dynamic systems by unfolding the video frames into column vectors and describing their trajectory as time evolves. After the projection of the vectors onto a lower dimensional space by a singular value decomposition (SVD), the trajectory is modeled using system identification techniques. Synthesis is obtained by driving the system with random noise. In this paper, we show that the standard SVD can be replaced by a higher order SVD (HOSVD), originally known as Tucker decomposition. HOSVD decomposes the dynamic texture as a multidimensional signal (tensor) without unfolding the video frames on column vectors. This is a more natural and flexible decomposition, since it permits us to perform dimension reduction in the spatial, temporal, and chromatic domain, while standard SVD allows for temporal reduction only. We show that for a comparable synthesis quality, the HOSVD approach requires, on average, five times less parameters than the standard SVD approach. The analysis part is more expensive, but the synthesis has the same cost as existing algorithms. Our technique is, thus, well suited to dynamic texture synthesis on devices limited by memory and computational power, such as PDAs or mobile phones.