NLCMAP: A Framework For The Efficient Mapping of Non-Linear Convolutional Neural Networks On Fpga Accelerators
Giuseppe Aiello, Beatrice Bussolino, Emanuele Valpreda, Massimo Ruo Roch, Guido Masera, Maurizio Martina, Stefano Marsi
-
SPS
IEEE Members: $11.00
Non-members: $15.00Length: 00:11:04
This work addresses motion coding in end-to-end learned video compression. The efficiency of motion coding is critical at low bit rates, at which a large portion of the bitstream signals motion information. Most end-to-end learned video codecs adopt an intra-coding approach to coding motion information as individual optical flow maps. Some recent studies introduce predictive motion coding to encode optical flow map residuals. Still, motion coding remains an active research area for learned video compression. We present an incremental optical flow coding scheme. It first leverages an extrapolated flow together with the reference frame in estimating an incremental flow between the reference and the target frames for efficient motion coding. It then derives the final flow map for motion compensation by integrating the incremental and the extrapolated flows in a double-warping scheme. Experimental results on commonly used datasets show the superiority of our method over predictive motion coding and other advanced schemes.