Sorry, you need to enable JavaScript to visit this website.

As a new medium, Virtual Reality (VR) has attracted widespread attentions and research interests. More and more researchers have built their VR image/video database and devise related algorithms. However, the existing methods of VR video quality assessment are not very effective, and one of the most important reasons is that the database is not suitable. To this end, this paper proposes an efficient VR quality assessment method on self-built database.

Estimating physical activity (PA) intensity and energy expenditure (EE) is a problem that typically requires the use of wearable sensors such as a heart rate monitor, or accelerometer. We investigate the accuracy of a computer vision system using videos recorded from a pair of wearable video glasses to estimate PA strength and EE automatically using age, gender, speed, and activity cues. Age and gender are obtained using the Deep EXpectation network, while activity is estimated from joint angles and movement speed.

Colorization is a challenging task that has recently been tackled by deep learning. Line art colorization is particularly difficult because there is no grayscale value to indicate the color intensities as there is in black-and-white photograph images. When designing a character, concept artists often need to try different color schemes, however, colorization is a time-consuming task. In this article, we propose a semi-automatic framework for colorizing manga concept arts by letting concept artists try different color schemes and obtain colorized results in fashion time.

Performance of 6DoF pose estimation techniques from RGB/RGB-D images has improved significantly with sophisticated deep learning frameworks. These frameworks require large-scale training data based on real/synthetic RGB/RGB-D information. Difficulty of obtaining adequate training data has limited the scope of these frameworks for ubiquitous application areas. Also, fast pose estimation at inference time often requires high-end GPU(s) that restricts the scope for its application in mobile hardware.

We consider a problem that recovers a 2-D object and the underlying view angle distribution from its noisy projection tilt series taken at unknown view angles. Traditional approaches rely on the estimation of the view angles of the projections, which do not scale well with the sample size and are sensitive to noise. We introduce a new approach using the moment features to simultaneously recover the underlying object and the distribution of view angles.

In this paper, we propose an approach for segmentation of challenging depth images. We first use a semi-automatic segmentation algorithm that only takes a user-defined rectangular area as an input. The quality of the segmentation is very heterogeneous at this stage, and unsufficient to efficiently train a neural network. We thus introduce a learning process that takes this imperfect nature of data into account, by iteratively filtering the dataset to only keep the best segmented images. We show this method improves the neural network’s performance by a significant amount.

With the prosperous development of deep learning, people pay more attention to the needs of different training data. In
this paper, we propose a method to automatically generate realistic training data for industrial components detection. Our