Takeo Igarashi

The University of Tokyo | Todai · Department of Computer Science

Recently, there has been a growing emphasis on autonomous vehicles (AVs), and as they coexist with pedestrians, ensuring pedestrian safety at crosswalks has become paramount. While AVs exhibit commendable performance on traditional roads with established traffic infrastructure, their interaction in different environments, such as shared spaces lack...

We introduce an interactive tool to intuitively make inbetween charts for cutout character movements (i.e., transitioning from one image to another), inspired by cartoon animators’ techniques. Given several keyframes, this system constructs trajectory-guided sliders that enable users to directly adjust inbetween values on a screen. In addition, the...

In autonomous vehicles (AVs), ensuring pedestrian safety within intricate and dynamic settings, particularly at crosswalks, has gained substantial attention. While AVs perform admirably in standard road conditions, their integration into unique environments like shared spaces devoid of traditional traffic infrastructure control presents complex cha...

Recently, there has been a growing emphasis on autonomous vehicles (AVs), and as they coexist with pedestrians, ensuring pedestrian safety at crosswalks has become paramount. While AVs exhibit commendable performance on traditional roads with established traffic infrastructure, their interaction in different environments, such as shared spaces lack...

Interface icons are prevalent in various digital applications. Due to limited time and budgets, many designers rely on informal evaluation, which often results in poor usability icons. In this paper, we propose a unique human‐in‐the‐loop framework that allows our target users, that is novice and professional user interface (UI) designers, to improv...

We propose Inkjet 4D Print, a self-folding fabrication method of 3D origami tessellations by printing 2D patterns on both sides of a heat-shrinkable base sheet, using a commercialized inkjet ultraviolet (UV) printer. Compared to the previous folding-based 4D printing approach using fused deposition modeling (FDM) 3D printers [An et al. 2018], our m...

Advancements in Vehicle-to-Infrastructure (V2I) and Vehicle-to-Everything (V2X) have improved in-vehicle information systems’ ability to provide drivers with global information. Although most global information does not worth a high priority, such as how many empty parking lots are available, the prediction of a potential traffic accident in the ne...

Interface icons are prevalent in various digital applications. Due to limited time and budgets, many designers rely on informal evaluation, which often results in poor usability icons. In this paper, we propose a unique human-in-the-loop framework that allows our target users, i.e., novice and professional UI designers, to improve the usability of...

Background Reproducibility of data analysis workflow is a key issue in the field of bioinformatics. Recent computing technologies, such as virtualization, have made it possible to reproduce workflow execution with ease. However, the reproducibility of results is not well discussed; that is, there is no standard way to verify whether the biological...

Animating 3D characters using motion capture data requires basic expertise and manual labor. To support the creativity of animation design and make it easier for common users, we present a sketch-based interface DualMotion, with rough sketches as input for designing daily-life animations of characters, such as walking and jumping. Our approach enab...

The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning. While voxel-based deep learning frameworks have been proposed for this segmentation task, their performance remains limited. In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly better results. Our propose...

Background: Many open-source workflow systems have made bioinformatics data analysis procedures portable. Sharing these workflows provides researchers easy access to high-quality analysis methods without the requirement of computational expertise. However, published workflows are not always guaranteed to be reliably reusable. Therefore, a system i...

The cover image is based on the Research Article Interactive texture editing for garment line drawings by Tsukasa Fukusato et al., https://doi.org/10.1002/cav.2117

Background Reproducibility of data analysis workflow is a key issue in the field of bioinformatics. Recent computing technologies, such as virtualization, have made it possible to reproduce workflow execution with ease. However, the reproducibility of results is not well discussed; that is, there is no standard way to verify whether the biological...

It is important to consider curvature properties around the control points to produce natural-looking results in the vector illustration. C² interpolating splines satisfy point interpolation with local support. Unfortunately, they cannot control the sharpness of the segment because it utilizes trigonometric function as blending function that has no...

Image registration is an essential part of Medical Image Analysis. Traditional local search methods (e.g., Mean Square Errors (MSE) and Normalized Mutual Information (NMI)) achieve accurate registration but require good initialization. However, finding a good initialization is difficult in partial image matching. Recent deep learning methods such a...

Animating 3D characters using motion capture data requires basic expertise and manual labor. To support the creativity of animation design and make it easier for common users, we present a sketch-based interface DualMotion, with rough sketches as input for designing daily-life animations of characters, such as walking and jumping.Our approach enabl...

The increased demand for efficient computation in data analysis encourages researchers in biomedical science to use workflow systems. Workflow systems, or so-called workflow languages, are used for the description and execution of a set of data analysis steps. Workflow systems increase the productivity of researchers, specifically in fields that us...

Adding two‐dimensional (2D) textures to garment line drawings (e.g., cartoon characters) remains challenging in the production pipeline of comics and illustrations since garment line drawings often have self‐occluded wrinkles. Although several techniques that can automatically deform and map 2D texture patterns to 2D line drawings have been propose...

We present a procedural framework for modeling the annual ring pattern of solid wood with knots. Although wood texturing is a well-studied topic, there have been few previous attempts at modeling knots inside the wood texture. Our method takes the skeletal structure of a tree log as input and produces a three-dimensional scalar field representing t...

Background Many open-source workflow systems have made bioinformatics data analysis procedures portable. Sharing these workflows provides researchers easy access to high-quality analysis methods without the requirement of computational expertise. However, published workflows are not always guaranteed to be reliably reusable. Therefore, a system is...

Polygonal modeling is a core task of content creation in Computer Graphics. The complexity of modeling, in terms of the number and the order of operations and time required to execute them makes it challenging to learn and execute. Our goal is to automatically derive a polygonal modeling sequence for a given target. Then, one can learn polygonal mo...

Reinforcement Learning (RL) is a machine learning approach based on how humans and animals learn new behaviors by actively exploring their environment that provides them positive and negative rewards. The interactive RL approach incorporates a human-in-the-loop that can guide a learning RL-based agent to personalize its behavior and/or speed up its...

Selecting colors is crucial for creating digital illustrations. However, achieving the desired colors, especially for inexperienced users, is difficult because the process involves unintuitive tuning of multiple parameters. In this paper, we propose an interactive color manipulation method allowing users to explore a color space using color modifie...

Virtual try-on is a promising application of computer graphics and human computer interaction that can have a profound real-world impact especially during this pandemic. Existing image-based works try to synthesize a try-on image from a single image of a target garment, but it inherently limits the ability to react to possible interactions. It is d...

Fig. 1: Our interactive explanations framework. Abstract-Reinforcement learning techniques successfully generate convincing agent behaviors, but it is still difficult to tailor the behavior to align with a user's specific preferences. What is missing is a communication method for the system to explain the behavior and for the user to repair it. In...

Writing high-performance image processing code is challenging and labor-intensive. The Halide programming language simplifies this task by decoupling high-level algorithms from "schedules" which optimize their implementation. However, even with this abstraction, it is still challenging for Halide programmers to understand complicated scheduling str...

In this paper, we propose a generic framework that enables game developers without knowledge of machine learning to create bot behaviors with playstyles that align with their preferences. Our framework is based on interactive reinforcement learning (RL), and we used it to create a behavior authoring tool called MarioMix. This tool enables non-exper...

Reinforcement learning techniques successfully generate convincing agent behaviors, but it is still difficult to tailor the behavior to align with a user's specific preferences. What is missing is a communication method for the system to explain the behavior and for the user to repair it. In this paper, we present a novel interaction method that us...

Interactive reinforcement learning (RL) has been successfully used in various applications in different fields, which has also motivated HCI researchers to contribute in this area. In this paper, we survey interactive RL to empower human-computer interaction (HCI) researchers with the technical background in RL needed to design new interaction tech...

OmniAD [Martin et al. 2015] is a data-driven pipeline for physics-based aerodynamics animations. In the pipeline, a real-time aerodynamic model which handles omni-directional airflow has also been introduced. However, their framework requires a captured motion, which implies that their model is not suitable for designing a customized motion. In thi...

Adding texture to a line drawing is an important process in the production of comics and illustrations. Garment drawings especially often have large deformations with self-occlusions, so deforming patterns is essential for representing realistic garment designs. However, it is currently done manually and requires a significant amount of effort by e...

We present a method to add distorted perspective effects for scenes with a forward camera dolly (the camera moves in the depth direction). Our target scene is a first-person view of the main character traversing a long path. A distorted perspective has been applied to such scenes in hand-drawn animation films to create more dynamic and dramatic mot...

In this paper, we propose a generic framework that enables game developers without knowledge of machine learning to create bot behaviors with playstyles that align with their preferences. Our framework is based on interactive reinforcement learning (RL), and we used it to create a behavior authoring tool called MarioMix. This tool enables non-exper...

We present Tsugite — an interactive system for designing and fabricating wood joints for frame structures. To design and manually craft such joints is difficult and time consuming. Our system facilitates the creation of custom joints by a modeling interface combined with computer numerical control (CNC) fabrication. The design space is a 3D grid of...

This paper introduces an interactive framework to design low-poly 3D models from 2D model sheets, which shows how the model (e.g., sketched characters) looks from the front and side. First, we made a prototype tool for 2D artists, without 3D modeling skill, to generate 3D point sets from 2D model sheets. This tool is simple but still useful for art...

This paper introduces a generative model for 3D surfaces based on a representation of shapes with mean curvature and metric, which are invariant under rigid transformation. Hence, compared with existing 3D machine learning frameworks, our model substantially reduces the influence of translation and rotation. In addition, the local structure of shap...

Game designers take into account the wide range of play-styles and skill levels of players to create enjoyable experiences. One important step in the game design process involves playtests with professional testers; this process is time-consuming and expensive. Hence, there exist several methods to create synthetic testers to test a game automatica...

Interactive reinforcement learning (RL) has been successfully used in various applications in different fields, which has also motivated HCI researchers to contribute in this area. In this paper, we survey interactive RL to empower human-computer interaction (HCI) researchers with the technical background in RL needed to design new interaction tech...

The development of a statistical modeling program requires example data to observe and verify the behavior of the program. Such example data are either taken from an existing dataset or synthesized using commands. Programmers may want to directly design an arbitrary dataset or modify it interactively, but it is difficult to do so in current develop...

The Halide programming language simplifies the implementation of high performance image processing by decoupling high-level algorithms from their schedules. Although writing a high-level algorithm is straightforward in Halide, writing a low-level scheduling strategy for optimizing the performance often requires many trials-and-errors and is difficu...

Although 3D texture painting has an advantage of making it easy to grasp the overall shape compared with a method of drawing directly onto a UV map, a disadvantage is unpainted (or distorted) regions appearing in the result due to, for example, self-occluded parts. Thus, in order to perform painting without leaving unpainted parts, sequential chang...

Wire sculpture is a unique art form where an artist represents a 3D form using 1D wires. However, the design of novel wire sculpture is difficult and limited to talented experts. We introduce a computer-assisted framework for manually creating 3D wire bending art from given 3D models. Our method extracts a set of 3D contour-curves from several view...

Artificial intelligence (AI) such as deep learning has achieved significant success in a variety of application domains. Several visualization techniques have been proposed for understanding the overall behavior of the neural network defined by deep learning code. However, they show visualization only after the code or network definition is written...

We introduce an interactive system to design 2D data sets on a scatter plot. 2D data sets are often used to obtain an intuition about the behavior of machine learning techniques or statistical modeling techniques . A traditional method for creating a data set is to use textural commands, such as generating a normal distribution with specific parame...

We propose a design and fabrication system leveraging the diverse shapes of natural wood. With our system, precise geometries are fabricated from non-standardized, naturally curved branches. In this way, low-valued tree branches are up-cycled to a construction material. The process is implemented as follows. Taking a set of branches and a user-defi...

" Speech is a direct and intuitive method to control a robot. While natural speech can capture a rich variety of commands, verbal input is poorly suited to finer grained and real-time control of continuous actions such as short and precise motion commands. For these types of operations, continuous non-verbal speech is more suitable, but it lacks th...

Deep neural networks (DNNs) have a high accuracy on image classification tasks. However, DNNs trained by such dataset with co-occurrence bias may rely on wrong features while making decisions for classification. It will greatly affect the transferability of pre-trained DNNs. In this paper, we propose an interactive method to direct classifiers payi...

Computational fabrication devices make the production of high-quality artifacts accessible to everyone. However, the design of these artifacts still requires skills and experience, making it difficult for individuals to design customized artifacts that satisfy their specific needs. To address this problem, our group has been developing various easy...

We present an interactive tool to model a returning boomerang envisioned by a user. Designing a functional and fashionable boomerang requires the computation of aerodynamics based on fluid simulation, but this computation remains difficult for interactive designs. Hence, we employ a data-driven approach [Nakamura et al. 2016; Umetani et al. 2014] b...

We present a system that facilitates asymmetric collaboration among users with two different viewpoints in the design of living or working spaces. One viewpoint is that of the space designers, who observe and alter the space from a top-down view using a large table-top interface. The other viewpoint is that of a space occupant, who observes the spa...

We introduce dynamically warping grids for adaptive liquid simulation. Our primary contributions are a strategy for dynamically deforming regular grids over the course of a simulation and a method for efficiently utilizing these deforming grids for liquid simulation. Prior work has shown that unstructured grids are very effective for adaptive fluid...

There are increasing needs in communication between an autonomous car and a pedestrian. Some conceptual solutions have been proposed to solve this issue, such as using various communication modalities (eyes, smile, text, light and projector) on a car to communicate with pedestrians. However, there is no detailed study in comparing these communicati...

The objective of the present research is to observe to what extent the stereoscopic effect presents a solution for enhancement of user interactions in the Web context. This paper describes an experiment conducted to detect differences in perception between 2D and 3D graphical user interfaces of an e-Commerce web application. The results of the cond...

We introduce a new advection scheme for fluid animation. Our main contribution is the use of long-term temporal changes in pressure to extend the commonly used semi-Lagrangian scheme further back along the time axis. Our algorithm starts by tracing sample points along a trajectory following the velocity field backwards in time for many steps. Durin...