In this supplementary material we first (Section 2) describe the details of a variant of scene carving (Sc. Carve-D.) not fully described in the paper but mentioned in Sect. 5.2 and Fig. 8(f) and Fig. 8(g). This algorithm aims to minimize the visible distortion in the next image, in contrast to the scene carving algorithm (Sc. Carve) we present in the paper in which the distortion in the backgr...

This paper presents a novel image retargeting approach for ranging cameras. The proposed approach first extracts three feature maps: depth map, saliency map, and gradient map. Then, the depth map and the saliency map are used to separate the main contents and the background and thus compute a map of saliency objects. After that, the proposed approach constructs an importance map which combines ...

Nowadays, images are being viewed on the slimmest and the smallest display devices which is a challenge for various image resizing techniques and algorithms. Traditional methods have been used to change the height and width of the image which are ignorant to the content of the image. Effective resizing of images should focus on image content more than anything else. A manageable technique calle...

In this paper we propose a method for dynamic rescaling of music, inspired by recent works on image retargeting, video reshuffling and character animation in the computer graphics community. Given the desired target length of a piece of music and optional additional constraints such as position and importance of certain parts, we build on concepts from seam carving, video textures and motion gr...

Motion Retargeting is a movement edition technology that designed for motion capture data of the production of computer animation. The technology of Motion Retargeting now has two problems--large databases and the complexity of the algorithm increased rapidly with the joints increasing. According to this, we propose a new method, Vector-Mapping method of motion retargeting. The initial movement...

This paper presents a new inverse kinematics method that utilizes the motion data for realtime control and editing. The key idea is to extract parameters necessary for inverse kinematics from the motion data. These parameters are the weight matrix, which determines the motion of the redundant joints, and the transformation functions that define the motion of the end effectors. User can control ...

Inappropriate lighting is often responsible for poor quality video. In most offices and homes, lighting is not designed for video conferencing. This can result in unevenly lit faces, distracting shadows, and unnatural colors. We present a method for relighting faces that reduces the effects of uneven lighting and color. Our setup consists of a compact lighting rig and a camera that is both inex...