All-in-focus with directional-max-gradient flow and labeled iterative depth propagation

By Guijin Wang, Wentao Li, Xuanwu Yin, Huazhong Yang. 2018

143 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

DeepXplore: Automated Whitebox Testing of Deep Learning Systems (2017, methodology): “Gradients have been used in the past for visualizing activation of different intermediate layers of a DNN for tasks like object segmentation [44, 66], artistic style transfer between two images [24, 43, 59], etc.”
Video-to-Video Synthesis (2018, methodology): “Video style transfer [10,22,28,58], transferring the style of a reference painting to a natural scene video, is also related.”
Exploring the structure of a real-time, arbitrary neural artistic stylization network (2017, background): “In addition, in a real time video, one could train the network to enforce temporal consistency between frames by appending additional loss functions [22].”
Fast Patch-based Style Transfer of Arbitrary Style (2016, methodology): “As a result, our method is able to adapt to video without any explicit gluing procedure like optical flow [30].”
TokenFlow: Consistent Diffusion Features for Consistent Video Editing (2023, methodology): “…video extensively repeat across frames [43, 7], and thus consistent editing can by simpliﬁed by editing a subset of keyframes and propagating the edit across the video by establishing patch correspondences using handcrafted features and optical ﬂow [40] or by training a patch-based GAN [50].”
Coherent Online Video Style Transfer (2017, methodology): “• Our feed-forward network is thousands of times faster compared to optimization-based style transfer in videos [1, 37], reaching 15 fps on modern GPUs.”
Avatar-Net: Multi-scale Zero-Shot Style Transfer by Feature Decoration (2018, background): “Despite visual appealing performances for arbitrary style, the results are not stable [24, 30] and the perceptual loss usually requires careful parameter tunning for different styles [10].”
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer (2021, methodology): “, [30] for optimization based video style transfer, [31, 1, 12, 13, 8] for per-style-per-model methods, [37, 38] for arbitrary-style-per-model methods, and [36, 4, 26] for image-to-image translation frameworks.”
Neural Style Transfer: A Review (2017, background): “Another work aimed at extending the Neural Style Transfer algo-rithm of Gatys et al . from still images to video sequences is given in [40] by Ruder et al. , which is referred to as Neural Video Style Transfer in our paper.”
Synthesising Dynamic Textures using Convolutional Neural Networks (2017, background): “Possibly spatio-temporal CNN features or the inclusion of optical flow measures [13] might help to model temporal dependencies of that kind.”
Consistent video depth estimation (2020, background): “In light of this, various approaches for enforcing temporal consistency have been developed in the context of style transfer [Chen et al. 2017; Huang et al. 2017; Ruder et al. 2016], image-based graphics applications [Lang et al.”
Artistic Style Transfer for Videos and Spherical Images (2017, methodology): “In an earlier conference version of the present paper, we demonstrated for the first time the capability of the optimization-based approach to stylize videos in a consistent way by incorporating additional loss functions into the objective function [22].”
Demystifying Neural Style Transfer (2017, background): “It achieved impressive results and several follow-up works improved upon this innovative approaches [11, 27, 21, 13].”
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization (2017, background): “[45] improved the quality 2017 IEEE International Conference on Computer Vision”