We present two extensions to the Space Carving framework. The first is a progressive scheme to better reconstruct surfaces lacking sufficient textures. The second is a novel photo-consistency measure that is valid for both specular and diffuse surfaces, under unknown lighting conditions. 1

GAZE-2 is a novel group video conferencing system that uses eye-controlled camera direction to ensure parallaxfree transmission of eye contact. To convey eye contact, GAZE-2 employs a video tunnel that allows placement of cameras behind participant images on the screen. To avoid parallax, GAZE-2 automatically directs the cameras in this video tunnel using an eye tracker, selecting a single camera closest to where the user is looking for broadcast. Images of users are displayed in a virtual meeting room, and rotated towards the participant each user looks at. This way, eye contact can be conveyed to any number of users with only a single video stream per user. We empirically evaluated whether eye contact perception is affected by automated camera direction, which causes angular shifts in the transmitted images. Findings suggest camera shifts do not affect eye contact perception, and are not considered highly distractive.

A new algorithm is proposed for novel view generation in one-toone teleconferencing applications. Given the video streams acquired by two cameras placed on either side of a computer monitor, the proposed algorithm synthesises images from a virtual camera in arbitrary position (typically located within the monitor) to facilitate eye contact.

Abstract not found

We propose a novel method to synthesize free-viewpoint images for a moving object, which is captured by uncalibrated multiple moving cameras. If multiple fixed cameras are used for capturing a moving object, we must zoom out in order to capture the moving object within FOV of the cameras. Such zooming-out limits the resolution for the moving object in the captured images. In the proposed method, we use multiple moving cameras that capture the moving object in the center of the images with high resolution. For shape reconstruction of the object from the uncalibrated multiple moving camera images, two fixed cameras are employed for determining Projective Grid Space, which defines a projective 3D coordinate in the object space. The coordinate in PGS can be related to every moving camera by fundamental matrices between the moving camera and the fixed cameras. In the experiment that is performed for demonstrating the efficacy of the proposed method, high resolution freeviewpoint images can be successfully synthesized by the proposed method. 1.

The lack of eye contact in video conference degrades the user’s experience. This problem has been known and studied for many years. There are hardware-based solutions to the eye gazing problem. However, these specialized systems are not generally accessible. This paper suggests a software approach that rectifies the face and the eyes in video conference, only utilizing one camera. In the setup phase, the view point and the affine transform matrix are calculated, using five frames each from the front view and the above view, with the aids of face detection and eye detection algorithm. Once the setup is done, we rectify the face with affine transformation, and rectify the eyes using image warping, based on an eye model. This is done in near real time (18 frames per second, for the resolution of 320x240). The result is not genuine but is significantly better. 1.

Web conferencing systems (WCSs) have entered a golden age of rapid development, as evidenced by more than a dozen commercial products and an expanding consumer population in the past five years. While WCSs have revolutionized the way people communicate and collaborate, there is still a lot of room for improvement in both the technologies and the users experience. In this paper, we summarize the latest achievements in WCS design and implementation from both scientific research and technical engineering, identify open questions and key challenges that deserve more research attention, and discuss interesting directions to explore for better solutions. We envision this paper will stimulate more researchers to explore ubi-media collaboration via WCS.

A new algorithm is proposed for efficient stereo and novel view synthesis. Given the video streams acquired by two synchronized cameras the proposed algorithm synthesises images from a virtual camera in arbitrary position near the physical cameras. The new technique is based on an improved, dynamic-programming, stereo algorithm for efficient novel view generation. The two main contributions of this paper are: i) a new four state matching graph for dense stereo dynamic programming, that supports accurate occlusion labelling; ii) a compact geometric derivation for novel view synthesis by direct projection of the minimum cost surface. Furthermore, the paper presents an algorithm for the temporal maintenance of a background model to enhance the rendering of occlusions and reduce temporal artefacts (flicker); and a cost aggregation algorithm that acts directly in the three-dimensional matching cost space. The proposed algorithm has been designed to work with input images with large disparity range, a common practical situation. The enhanced occlusion handling capabilities of the new dynamic programming algorithm are evaluated against those of the most powerful state-of-the-art dynamic programming and graph-cut techniques. Four-state DP is also evaluated against the disparity-based Middlebury error metrics and its performance found to be amongst the best of the efficient algorithms. A number of examples demonstrate the robustness of four-state DP to artefacts in stereo video streams. This includes demonstrations of cyclopean view synthesis in extended conversational sequences, synthesis from a freely translating virtual camera and, finally, basic 3D scene editing.