FRAME INTERPOLATION VIA ADAPTIVE CONVOLUTION AND ADAPTIVE SEPARABLE CONVOLUTION

WIPO Patent Application WO/2018/170393

A3

Systems, methods, and computer-readable media for context-aware synthesis for video frame interpolation are provided. A convolutional neural network (ConvNet) may, given two input video or image frames, interpolate a frame temporarily in the middle of the two input frames by combining motion estimation and pixel synthesis into a single step and formulating pixel interpolation as a local convolution over patches in the input images. The ConvNet may estimate a convolution kernel based on a first receptive field patch of a first input image frame and a second receptive field patch of a second input image frame. The ConvNet may then convolve the convolutional kernel over a first pixel patch of the first input image frame and a second pixel patch of the second input image frame to obtain color data of an output pixel of the interpolation frame. Other embodiments may be described and/or claimed.

LIU FENG (US)
NIKLAUS SIMON (US)
MAI LONG (US)

PCT/US2018/022858

December 20, 2018

March 16, 2018

Click for automatic bibliography generation  

UNIV PORTLAND STATE (US)

G06T1/40

WO2016132146A1

2016-08-25

HAITAM BEN YAHIA: "Frame Interpolation using Convolutional Neural Networks on 2D animation", BACHELOR THESIS, 24 June 2016 (2016-06-24), XP055558906
GUCAN LONG ET AL.: "Learning Image Matching by Simply Watching Video", ECCV 2016, 2016, pages 434 - 450, XP047355274

STRAUSS, Ryan, N. et al. (US)

View/Download PDF      PDF Help

Previous Patent: METHOD FOR DECREASING BUBBLE LIFETIME ON A GLASS MELT SURFACE

Next Patent: COMPOSITIONS AND METHODS FOR WOUND HEALING