Spherical images taken in all directions (360 degrees by 180 degrees) can represent an entire space including the subject, providing free direction viewing and an immersive experience to viewers. It is convenient and expands the usage scenarios to generate a spherical image from a few normal-field-of-view (NFOV) images, which are partial observations. The primary challenge is generating a plausible image and controlling the high degree of freedom involved in generating a wide area that includes all directions. We focus on scene symmetry, which is a basic property of the global structure of spherical images, such as the rotational and plane symmetries. We propose a method for generating a spherical image from a few NFOV images and controlling the generated regions using scene symmetry. We incorporate the intensity of the symmetry as a latent variable into conditional variational autoencoders to estimate the possible range of symmetry and decode a spherical image whose features are represented through a combination of symmetric transformations of the NFOV image features. Our experiments show that the proposed method can generate various plausible spherical images controlled from asymmetrically to symmetrically, and can reduce the reconstruction errors of the generated images based on the estimated symmetry.

Spherical images taken in all directions (360 degrees by 180 degrees) allow the full surroundings of a subject to be represented, providing an immersive experience to viewers. Generating a spherical image from a single normal-field-of-view (NFOV) image is convenient and expands the usage scenarios considerably without relying on a specific panoramic camera or images taken from multiple directions; however, achieving such images remains a challenging and unresolved problem. The primary challenge is controlling the high degree of freedom involved in generating a wide area that includes all directions of the desired spherical image. We focus on scene symmetry, which is a basic property of the global structure of spherical images, such as rotational symmetry, plane symmetry, and asymmetry. We propose a method for generating a spherical image from a single NFOV image and controlling the degree of freedom of the generated regions using the scene symmetry. To estimate and control the scene symmetry using both a circular shift and flip of the latent image features, we incorporate the intensity of the symmetry as a latent variable into conditional variational autoencoders. Our experiments show that the proposed method can generate various plausible spherical images controlled from symmetric to asymmetric, and can reduce the reconstruction errors of the generated images based on the estimated symmetry.

This paper presents a novel denoising algorithm for color images. It is difficult to reduce color noise at high speed without losing image details. To solve this problem, the proposed method employs maximum a posteriori (MAP) estimation based on a Gaussian model in ε-neighborhood of the pixel and CIELAB color space. Using the correlation between RGB components in ε-neighborhood, color noise is reduced efficiently. Computational complexity is low because the method consists of non-iterative filtering and simple matrix operations. Experiments confirm that the proposed method preserves more image details, delivers PSNR close to state-of-the-art denoising algorithms, and involves less computation.

Adaptation of biological systems can be viewed as decreasing local interaction among subsystems to realize effective cooperation. Conversely, it is important for effective cooperation to evaluate and control local interaction. Based on this idea we present a method of realizing cooperative rope turning by a man and a manipulator. The rotating motion of the manipulator arm for rope turning can be specified by frequency and phase difference between the arm and the rope. The frequency is determined in real-time by rhythm entrainment using a phase-locked loop. The phase difference is related to the quantity of local inter-action, that is, energy transfer from the arm to the rope. Therefore it is controlled to realize desired energy transfer, which is estimated from human demonstration. In the experiment the manipulator can successfully adapt its motion to that of the human partner.

A control method of robots for human-robot cooperative manipulation is investigated. We propose estimating human motion using the minimum jerk model for smooth cooperation. Using a nonlinear least-squares method, we identify two parameters of the minimum jerk model in real-time. The estimated position of the human hand is used to determine the desired position of the end-effector of the manipulator in virtual compliance control. The effectiveness of the proposed method is verified by experimentation with an industrial 6-degree-of-freedom manipulator. Energy transfer in cooperative manipulation is studied for quantitative evaluation of achieved cooperation from the viewpoint of adaptation theory.