Pixel-level Semantics Guided Image Colorization

08/05/2018
by   Jiaojiao Zhao, et al.
6

While many image colorization algorithms have recently shown the capability of producing plausible color versions from gray-scale photographs, they still suffer from the problems of context confusion and edge color bleeding. To address context confusion, we propose to incorporate the pixel-level object semantics to guide the image colorization. The rationale is that human beings perceive and distinguish colors based on the object's semantic categories. We propose a hierarchical neural network with two branches. One branch learns what the object is while the other branch learns the object's colors. The network jointly optimizes a semantic segmentation loss and a colorization loss. To attack edge color bleeding we generate more continuous color maps with sharp edges by adopting a joint bilateral upsamping layer at inference. Our network is trained on PASCAL VOC2012 and COCO-stuff with semantic segmentation labels and it produces more realistic and finer results compared to the colorization state-of-the-art.

READ FULL TEXT

page 2

page 3

page 7

page 9

page 10

research
01/27/2019

Pixelated Semantic Colorization

While many image colorization algorithms have recently shown the capabil...
research
06/13/2020

Semantic-driven Colorization

Recent deep colorization works predict the semantic information implicit...
research
11/29/2019

Color inference from semantic labeling for person search in videos

We propose an explainable model to generate semantic color labels for pe...
research
11/18/2017

Transferable Semi-supervised Semantic Segmentation

The performance of deep learning based semantic segmentation models heav...
research
07/08/2020

A Multi-Level Approach to Waste Object Segmentation

We address the problem of localizing waste objects from a color image an...
research
07/06/2015

Joint Calibration for Semantic Segmentation

Semantic segmentation is the task of assigning a class-label to each pix...
research
04/18/2023

Motion-state Alignment for Video Semantic Segmentation

In recent years, video semantic segmentation has made great progress wit...

Please sign up or login with your details

Forgot password? Click here to reset