Figure 1: Images of a soccer game. Upper part shows pseudo-dolly video by proposed method. In the pseudo-dolly-in video, motion parallax can be reproduced and the depth can be understood. Furthermore, since the reconstruction process is applied to the missing region, the proposed method maintains the image quality. Lower figure shows digital zoom image. When comparing with digital zoom image and proposed method, in the proposed method, the players are rendered at (relatively) geometrically correct positions as if the camera goes in to the field (dolly-in).
ABSTRACTThis paper proposes a pseudo-dolly-in video generation method that reproduces motion parallax by applying image reconstruction processing to multi-view videos. Since dolly-in video is taken by moving a camera forward to reproduce motion parallax, we can present a sense of immersion. However, at a sporting event in a large-scale space, moving a camera is difficult. Our research generates dolly-in video from multi-view images captured by fixed cameras. By applying the Image-Based Modeling technique, dollyin video can be generated. Unfortunately, the video quality is often damaged by the 3D estimation error. On the other hand, Bullet-Time realizes high-quality video observation. However, moving the virtual-viewpoint from the capturing positions is difficult. To solve these problems, we propose a method to generate a pseudo-dollyin image by installing 3D estimation and image reconstruction techniques into Bullet-Time and show its effectiveness by applying it to multi-view videos captured at an actual soccer stadium. In the experiment, we compared the proposed method with digital zoom images and with the dolly-in video generated from the Image-Based Modeling and Rendering method.