Seg2pix: Few Shot Training Line Art Colorization with Segmented Image Data

Segmented Images Colorization Using Harmony

In the colorization process, artists fill image’s regions with colors following harmony rules. Some region colorizations are more significant than others. In this paper we introduce a model for computer assisted colorization of segmented images using Itten’s proportion contrast. Our model is able to process images composed of totally blank or partially filled regions. Though, each region must b...

Image Colorization

This project seeks to reproduce the work of [Levin] on colorization of a black and white image. The approach used takes two black and white images, which are identical except for color markings on one of them. The colored result is based on an optimization problem that has two sets of constraints: First, the color of pixels should be close to their marked color, if applicable. Second, the color...

Few-Shot Image Recognition by Predicting Parameters from Activations

In this paper, we are interested in the few-shot learning problem. In particular, we focus on a challenging scenario where the number of categories is large and the number of examples per novel category is very limited, i.e. 1, 2, or 3. Motivated by the close relationship between the parameters and the activations in a neural network associated with the same category, we propose a novel method ...

Image and Video Colorization

Natural Image Colorization

In this paper, we present an interactive system for users to easily colorize the natural images of complex scenes. In our system, colorization procedure is explicitly separated into two stages: Color labeling and Color mapping. Pixels that should roughly share similar colors are grouped into coherent regions in the color labeling stage, and the color mapping stage is then introduced to further ...