Object Movie Research Articles

Background Removal of Multiview Images by Learning Shape Priors

Image-based rendering has been successfully used to display 3-D objects for many applications. A well-known example is the object movie, which is an image-based 3-D object composed of a collection of 2-D images taken from many different viewpoints of a 3-D object. In order to integrate image-based 3-D objects into a chosen scene (e.g., a panorama), one has to meet a hard challenge--to efficiently and effectively remove the background from the foreground object. This problem is referred to as multiview images (MVIs) segmentation. Another task requires MVI segmentation is image-based 3-D reconstruction using multiview images. In this paper, we propose a new method for segmenting MVI, which integrates some useful algorithms, including the well-known graph-cut image segmentation and volumetric graph-cut. The main idea is to incorporate the shape prior into the image segmentation process. The shape prior introduced into every image of the MVI is extracted from the 3-D model reconstructed by using the volumetric graph cuts algorithm. Here, the constraint obtained from the discrete medial axis is adopted to improve the reconstruction algorithm. The proposed MVI segmentation process requires only a small amount of user intervention, which is to select a subset of acceptable segmentations of the MVI after the initial segmentation process. According to our experiments, the proposed method can provide not only good MVI segmentation, but also provide acceptable 3-D reconstructed models for certain less-demanding applications.

Content-Based Object Movie Retrieval and Relevance Feedbacks

Object movie refers to a set of images captured from different perspectives around a 3D object. Object movie provides a good representation of a physical object because it can provide 3D interactive viewing effect, but does not require 3D model reconstruction. In this paper, we propose an efficient approach for content-based object movie retrieval. In order to retrieve the desired object movie from the database, we first map an object movie into the sampling of a manifold in the feature space. Two different layers of feature descriptors, dense and condensed, are designed to sample the manifold for representing object movies. Based on these descriptors, we define the dissimilarity measure between the query and the target in the object movie database. The query we considered can be either an entire object movie or simply a subset of views. We further design a relevance feedback approach to improving retrieved results. Finally, some experimental results are presented to show the efficacy of our approach.

Combining image and model based rendering of an archaeological site

Preservation of cultural heritage through digital technology can only be successful if people can experience sites and reconstructions in an intuitive, yet convincingly realistic manner. A way to get people interested in the past is highlighting the link of the past with the present. In this paper, an entire pipeline is discussed that augments an existing Quicktime VR object movie of the virtual reconstruction of an archaeological site with images of the site as it exists today. The new images are generated using an image-based rendering approach.

Augmenting panoramas with object movies by generating novel views with disparity‐based view morphing

AbstractOur goal is to augment a panorama with object movies in a visually 3D‐consistent way. Notice that a panorama is recorded as one single 2D image and an object movie (OM) is composed of a set of 2D images taken around a 3D object. The challenge is how to integrate the above two sources of 2D images in a 3D‐consistent way so that the user can easily manipulate object movies in a panorama. To solve this problem, we adopt a purely image‐based approach that does not have to reconstruct the geometric models of the 3D objects to be inserted in the panorama. A critical issue of this method is how to generate the novel views required for showing an OM in different places of a panorama, and we have proposed a view morphing technique, called t‐DBVM, to solve this problem. Our experiments have shown that this purely image‐based approach can effectively generate visually convincing OM‐augmented panoramas. This method has great potential for many applications that require integration of panoramas and object movies, such as virtual malls, virtual museum, and interior design. Copyright © 2002 John Wiley & Sons, Ltd.

Using QuickTime virtual reality objects in computer-assisted instruction of gross anatomy: Yorick--the VR Skull.

QuickTime virtual reality (QTVR) is a software technology that creates, on a normal computer screen, the illusion of holding and turning a three-dimensional object. QTVR is a practical photo-realistic virtual reality technology that is easily implemented on any current personal computer or via the Internet with no special hardware requirements. Because of its ability to present dynamic photo-quality images, we reasoned that QTVR can provide a more realistic presentation of anatomic structure than two-dimensional atlas pictures and facilitate study of specimens outside the dissection lab. We created QTVR objects, using portions of the skull, and incorporated them into an instructional program for first-year medical students. To obtain images, the bones of the skull were mounted on a rotating table, and a digital camera was positioned on a swinging arm so that the focal point remained coincident with the rotational center of the object as the camera was panned through a vertical arc. Digital images were captured at intervals of 10 degrees rotation of the object (horizontal pan). The camera was then swung through an arc with additional horizontal pan sequences taken at 10 degrees intervals of vertical pan. The images were edited to place the object on a solid black background, then assembled into a linear QuickTime movie. The linear movie was processed to yield a QTVR object movie that can be manipulated on vertical and horizontal axes using the mouse. QTVR movies were incorporated into an interactive environment that provided labeling, links to text-based information and self-testing capabilities. This program, Yorick-the VR Skull, has been used in our first-year medical and graduate gross anatomy courses for the past two years. Results of student evaluation of the program indicate that this QTVR-based program is an effective learning tool that is well received by students.

Quicktime VR: A powerful new illustrative tool for micropaleontological research

Publication in electronic journals permits authors to substantially increase the number and type of methods used to illustrate important concepts. An example of one of these new techniques of illustration, only available electronically is QuickTime VR movies. Although too time consuming for routine micropaleontological illustration (about 6 hours per illustration), QuickTime VR object movies hold great promise for illustrating new species as these movies permit the viewer to rotate and view a virtual copy of the specimen from any angle. A specimen of the benthic forminifer Elphidium crispum (well documented and illustrated in scientific literature) was used to produce a series of digitally captured scanning electron images. The images were edited and assembled using Apple’s QuickTime VR Authoring Studio program. The process of assembling a QuickTime VR object movie is relatively simple and straightforward once the images are suitably prepared. Postproduction time can be significantly reduced if care is taken to mount the sample exactly in the center of the stub.