Channel Decomposition on Generative Networks

08/10/2019
by   Shih-Chieh Su, et al.
5

This work presents a method to decompose a layer of the generative networks into the painting actions. To behave like the human painter, these actions are driven by the cost simulating the hand movement, the paint color change, the stroke shape and the stroking style. To help planning, the Mask R-CNN is applied to detect the object areas and decide the painting order. The proposed painting system introduces a variety of extensions in artistic styles, based on the chosen parameters. Further experiments are performed to evaluate the channel penetration and the channel sensitivity on the strokes.

READ FULL TEXT

page 2

page 4

page 6

page 7

page 9

research
08/10/2019

Channel Decomposition into Painting Actions

This work presents a method to decompose a convolutional layer of the de...
research
04/25/2023

Text-guided Eyeglasses Manipulation with Spatial Constraints

Virtual try-on of eyeglasses involves placing eyeglasses of different sh...
research
03/26/2019

SRM : A Style-based Recalibration Module for Convolutional Neural Networks

Following the advance of style transfer with Convolutional Neural Networ...
research
11/21/2018

Computational Decomposition of Style for Controllable and Enhanced Style Transfer

Neural style transfer has been demonstrated to be powerful in creating a...
research
10/03/2016

Prediction of Manipulation Actions

Looking at a person's hands one often can tell what the person is going ...
research
11/07/2022

Humans decompose tasks by trading off utility and computational cost

Human behavior emerges from planning over elaborate decompositions of ta...
research
06/08/2021

Property-Aware Robot Object Manipulation: a Generative Approach

When transporting an object, we unconsciously adapt our movement to its ...

Please sign up or login with your details

Forgot password? Click here to reset