The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling approach to compress temporal sequences with a focus on video. Our approach builds upon variational autoencoder (VAE) models for sequential data and combines them with recent work on neural image compression.
In this work we propose a deep learning framework for color propagation that combines a local strategy, to propagate colors frame-by-frame ensuring temporal stability, and a global strategy, using semantics for color propagation within a longer range.
We propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning.
We present a new method for decomposing an image into a set of soft color segments that are analogous to color layers with alpha channels that have been commonly utilized in modern image manipulation software.
We propose an efficient STEA filtering pipeline based on the recently proposed permeability filter (PF) which offers high quality and halo reduction capabilities.
We introduce a spatial pyramid-like structure to the image and learn CNNs for image sub-regions at different scales.
We present a novel, purely affinity-based natural image matting algorithm.
We demonstrate that highly accurate object segmentation in videos can be enabled by using a convolutional neural network (convnet) trained with static images only.
We propose an end-to-end solution for presenting movie quality animated graphics to the user while still allowing the sense of presence afforded by free viewpoint head motion.
We revisit some key steps of this workflow and propose semiautomatic methods for performing them.
Page 1 of 9