This paper reports on two generative systems that work in the domain of textiles: the Hoopla system that generates patterns for embroidery samplers, and the Foundry system that creates foundation paper piecing patterns for quilts. Generated patterns are enacted and interpreted by the human who stitches the final product, following a long and laborious, yet entertaining and leisurely, process of stitching and sewing. The blending of digital and physical spaces, the tension between machine and human authorship, and the juxtaposition of stereotypically masculine computing with highly feminine textile crafts, leads to the opportunity for new kinds of tools, experiences, and artworks. This paper argues for the values of textiles as a domain for generative methods research, and discusses generalizable research problems that are highlighted through operating in this new domain.
Questions convey information about the questioner, namely what one does not know. In this paper, we propose a novel approach to allow a learning agent to ask what it considers as tricky to predict, in the course of producing a final output. By analyzing when and what it asks, we can make our model more transparent and interpretable. We first develop this idea to propose a general framework of deep neural networks that can ask questions, which we call asking networks. A specific architecture and training process for an asking network is proposed for the task of colorization, which is an exemplar one-to-many task and thus a task where asking questions is helpful in performing the task accurately. Our results show that the model learns to generate meaningful questions, asks difficult questions first, and utilizes the provided hint more efficiently than baseline models. We conclude that the proposed asking framework makes the learning agent reveal its weaknesses, which poses a promising new direction in developing interpretable and interactive models.
The idea is to give a grasp on some concepts that are necessary to understand what comes next without being too much detailed as a more detailed explanation is out of the scope of this post. Feel free to skip these parts if you already know what they're talking about. As previously anticipated a color can be represented as a point in an n-dimensional space called color space. Most commonly the space is 3-dimensional and the coordinates in that space can be used to encode a color. There are many color spaces for different purposes and with different gamut (range of colors), and in each of them it is possibile to define a distance metric that quantifies the color difference. The most common and easiest distance metric used is the Euclidean distance which is used in RGB and Lab color spaces. The RGB (abbreviation of red-green-blue) color space is by far the most common and used color space. The idea is that it is possibile to create colors by combining red, green and blue. A color in RGB is usually encoded as a 3-tuple of 8 bits each, hence each dimension takes a value within the range [0, 255] where 0 stands for absence of color while 255 stands for full presence of color.
Learning color mixing is difficult for novice painters. In order to support novice painters in learning color mixing, we propose a prediction model for semitransparent pigment mixtures and use its prediction results to create a Smart Palette system. Such a system is constructed by first building a watercolor dataset with two types of color mixing data, indicated by transmittance and reflectance: incrementation of the same primary pigment and a mixture of two different pigments. Next, we apply the collected data to a deep neural network to train a model for predicting the results of semitransparent pigment mixtures. Finally, we constructed a Smart Palette that provides easily-followable instructions on mixing a target color with two primary pigments in real life: when users pick a pixel, an RGB color, from an image, the system returns its mixing recipe which indicates the two primary pigments being used and their quantities.
The traditional story understanding dogma in AI holds that there exists a singular, objective meaning implied by text, which can be uncovered by applying just the right logical inferences. But according to research into the cognition of reading, text can also be read, not objectively, but aesthetically. An aesthetic reading of text engages not only the agency of thought, but also intuition, sensation, and sentiment, and cultural interpretation. We have developed and implemented a basic computational model of aesthetic reading, which employs Carl Jung's Modes of Interpretation idea to delegate the task of aesthetic interpretation out to several different textual analysis engines, each computing a different mode of interpreting text, such as generating sentimental evocations of a text (Feeling modality), or remembering visual imagery evoked by the text (Sensation modality). The outputs of the various interpretive modalities are merged and then their unification is achieved by mapping them into color space using theories of color psychology. We built the Aesthetiscope, an artwork whose grid of colors are dynamically generated from aesthetic readings of an inputted poem or song, to illustrate the power and potential of going beyond literal understandings of text.