Learned Video Compression Via Heterogeneous Deformable Compensation Network

Highly scalable video compression using a lifting-based 3D wavelet transform with deformable mesh motion compensation

This paper continues the development of a new framework for the construction of motion compensated wavelet transforms for highly scalable video compression. The current authors recently proposed a motion adaptive wavelet transform based on motioncompensated lifting steps. This approach overcomes several limitations of existing methods. In particular, frame warping and block displacement methods...

Lossless Compression of Video Using Motion Compensation

Fast Video Artistic Transfer via Motion Compensation

Techniques for conversion of natural video scenes into drawing-style videos are frequently used to produce animated movies. In the past, the conversion was manually performed, what demanded a lot of time and a high production cost. Recently, with the advancement of computer vision techniques and the development of new deep learning algorithms, 'drawing' can be automatically performed. Neverthel...

Data Compression by Shape Compensation for Mobile Video Sensors

Most security systems, with their transmission bandwidth and computing power both being sufficient, emphasize their automatic recognition techniques. However, in some situations such as baby monitors and intruder avoidance by mobile sensors, the decision function sometimes can be shifted to the concerned human to reduce the transmission and computation cost. We therefore propose a binary video ...

Motion compensation based on tangent distance prediction for video compression

We present, in this article, a new algorithm for motion compensation that uses a motion estimation method based on tangent distance. The method is compared with a BlockMatching based approach in various common situations. Whereas Block-Matching algorithms usually only predict positions of blocks over time, our method also predicts the evolution of pixels into these blocks. The prediction error ...