DeepAI AI Chat
Log In Sign Up

Temporally Coherent Person Matting Trained on Fake-Motion Dataset

by   Ivan Molodetskikh, et al.

We propose a novel neural-network-based method to perform matting of videos depicting people that does not require additional user input such as trimaps. Our architecture achieves temporal stability of the resulting alpha mattes by using motion-estimation-based smoothing of image-segmentation algorithm outputs, combined with convolutional-LSTM modules on U-Net skip connections. We also propose a fake-motion algorithm that generates training clips for the video-matting network given photos with ground-truth alpha mattes and background videos. We apply random motion to photos and their mattes to simulate movement one would find in real videos and composite the result with the background clips. It lets us train a deep neural network operating on videos in an absence of a large annotated video dataset and provides ground-truth training-clip foreground optical flow for use in loss functions.


page 1

page 4

page 5

page 6

page 7

page 9


Unsupervised Generation of Optical Flow Datasets from Videos in the Wild

Dense optical flow ground truth of non-rigid motion for real-world image...

Background Matting: The World is Your Green Screen

We propose a method for creating a matte – the per-pixel foreground colo...

Temporally Coherent Video Harmonization Using Adversarial Networks

Compositing is one of the most important editing operations for images a...

Visual Descriptor Learning from Monocular Video

Correspondence estimation is one of the most widely researched and yet o...

Disentangling Motion, Foreground and Background Features in Videos

This paper introduces an unsupervised framework to extract semantically ...

Application Of ADNN For Background Subtraction In Smart Surveillance System

Object movement identification is one of the most researched problems in...

RipViz: Finding Rip Currents by Learning Pathline Behavior

We present a hybrid machine learning and flow analysis feature detection...