Fumio Okura / 大倉 史生

We propose a method for inferring three-dimensional (3D) plant branch structures that are hidden under leaves from multi-view observations. Unlike previous geometric approaches that heavily rely on the visibility of the branches or use parametric branching models, our method makes statistical inferences of branch structures in a probabilistic framework. By inferring the probability of branch existence using a Bayesian extension of image-to-image translation applied to each of multi-view images, our method generates a probabilistic plant 3D model, which represents the 3D branching pattern that cannot be directly observed. Experiments demonstrate the usefulness of the proposed approach in generating convincing branch structures in comparison to prior approaches.

The performance of dual task, simultaneously performing two tasks, is a useful measure of a person's cognitive abilities because it creates a heavier load on the brain than single tasks. Large-scale datasets of dual-task behavior are required to quantitatively analyze the relationships among dual-task performance, cognitive functions, and personal attributes such as age. We developed an automatic data collection system for dual-task behavior that can be installed in public spaces or facilities. The system is designed as an entertainment kiosk to attract participants. We used the system to collect a large-scale dataset consisting of more than 70,000 sessions of dual-task behavior, in conjunction with a long-running exhibition in a science museum. The resultant dataset, which includes sensor data such as RGB-D image sequences, can be used for learning- and vision-based investigations of human cognitive functions.

Recent color transfer methods use local information to learn the transformation from a source to an exemplar image, and then transfer this appearance change to a target image. These solutions achieve very successful results for general mood changes, e.g., changing the appearance of an image from ''sunny'' to ''overcast''. However, such methods have a hard time creating new image content, such as leaves on a bare tree. Texture transfer, on the other hand, can synthesize such content but tends to destroy image structure. We propose the first algorithm that unifies color and texture transfer, outperforming both by leveraging their respective strengths. A key novelty in our approach resides in teasing apart appearance changes that can be modelled simply as changes in color versus those that require new image content to be generated. Our method starts with an analysis phase which evaluates the success of color transfer by comparing the exemplar with the source. This analysis then drives a selective, iterative texture transfer algorithm that simultaneously predicts the success of color transfer on the target and synthesizes new content where needed. We demonstrate our unified algorithm by transferring large temporal changes between photographs, such as change of season - e.g., leaves on bare trees or piles of snow on a street - and flooding.

Indirect augmented reality (IAR) employs a unique approach to achieve high-quality synthesis of the real world and the virtual world, unlike traditional augmented reality (AR), which superimposes virtual objects in real time. IAR uses pre-captured omnidirectional images and offline superimposition of virtual objects for achieving jitter- and drift-free geometric registration as well as high-quality photometric registration. However, one drawback of IAR is the inconsistency between the real world and the pre-captured image. In this paper, we present a new classification of IAR inconsistencies and analyze the effect of these inconsistencies on the IAR experience. Accordingly, we propose a novel IAR system that reflects real-world illumination changes by selecting an appropriate image from among multiple pre-captured images obtained under various illumination conditions. The results of experiments conducted at an actual historical site show that the consideration of real-world illumination changes improves the realism of the IAR experience.

This study proposes a framework for photorealistic synthesis of virtual objects and virtualized real-world. We combine the offline rendering of virtual objects and image-based rendering (IBR) to take advantage of the high quality of offline rendering without the computational cost of online CG rendering; i.e., it incurs only the cost of the online computation for IBR. Our IBR implementation reduces the computational costs required to online process by generating structured viewpoints (e.g., at every grid point).

This study proposes a teleoperation interface where an operator can control a robot from freely configured viewpoints using realistic images of the physical world. The viewpoints generated by the proposed interface provide human operators with intuitive control using a head-mounted display and head tracker, and assist them to grasp the environment surrounding the robot. A state-of-the-art free-viewpoint image generation technique is employed to generate the scene presented to the operator. In addition, an augmented reality technique is used to superimpose a 3D model of the robot onto the generated scenes.

This study proposes a method for acquiring full spherical high dynamic range (HDR) images without any missing areas by using two omnidirectional cameras mounted on the top and bottom of an unmanned airship. The full spherical HDR images are generated by combining multiple omnidirectional images that are captured with different shutter speeds. The images generated are intended for uses in immersive panorama and its augmentation with image-based lighting.

We propose a tone mapping method particularly for HDR images which have two spatially separated luminance distributions of bright and dark regions. We assume that human does not feel a sense of discomfort, even if luminance values between bright and dark regions is reversed, when these regions are definitely divided according to dimidiated luminance and spatial distributions. Under this assumption, we divide an HDR image into bright and dark regions and apply a different tone mapping function to each region independently.

We developed an augmented immersive panorama system which enables virtual tourism beyond time and space, where immersive panorama is a display method of omnidirectional panoramic images that enables us to look around from a location, like Google Street View. Our application provides a user with both the views of a remote location and related information using augmented reality techniques. This study deals with the geometric and photometric registration problems to generate high-quality augmented omnidirectional videos automatically. The user can look around the scene from the sky above Heijo Palace Site which is an ancient capital in Nara, Japan.

An omnidirectional multi-camera system (OMS) mounted on an unmanned airship captures aerial omnidirectional videos suitable for telepresence, augmented/mixed reality, and urban reconstruction. We developed a simple autopilot aerial imaging system.