Advancements in prediction of human motion sequences are critical for enabling online virtual reality (VR) users to dance and move in ways that accurately mirror real-world actions, delivering a more immersive and connected experience. However, latency in networked motion tracking remains a significant challenge, disrupting engagement and necessitating predictive solutions to achieve real-time synchronization of remote motions. To address this issue, we propose a novel approach leveraging a synthetically generated dataset based on supervised foot anchor placement timings for rhythmic motions, ensuring periodicity and reducing prediction errors. Our model integrates a discrete cosine transform (DCT) to encode motion, refine high-frequency components, and smooth motion sequences, mitigating jittery artifacts. Additionally, we introduce a feed-forward attention mechanism designed to learn from N-window pairs of 3D key-point pose histories for precise future motion prediction. Quantitative and qualitative evaluations on the Human3.6M dataset highlight significant improvements in mean per joint position error (MPJPE) metrics, demonstrating the superiority of our technique over state-of-the-art approaches. We further introduce novel result pose visualizations through the use of generative AI methods.

We propose an end-to-end solution for presenting movie quality animated graphics to the user while still allowing the sense of presence afforded by free viewpoint head motion. By transforming offline rendered movie content into a novel immersive representation, we display the content in real-time according to the tracked head pose. For each frame, we generate a set of cubemap images per frame (colors and depths) using a sparse set of of cameras placed in the vicinity of the potential viewer locations. The cameras are placed with an optimization process so that the rendered data maximise coverage with minimum redundancy, depending on the lighting environment complexity. We compress the colors and depths separately, introducing an integrated spatial and temporal scheme tailored to high performance on GPUs for Virtual Reality applications. A view-dependent decompression algorithm decodes only the parts of the compressed video streams that are visible to users. We detail a real-time rendering algorithm using multi-view ray casting, with a variant that can handle strong view dependent effects such as mirror surfaces and glass. Compression rates of 150:1 and greater are demonstrated with quantitative analysis of image reconstruction quality and performance.

Abstract We present several mixed‐reality‐based remote collaboration settings by using consumer head‐mounted displays. We investigated how two people are able to work together in these settings. We found that the person in the AR system will be regarded as the “leader” (i.e., they provide a greater contribution to the collaboration), whereas no similar “leader” emerges in augmented reality (AR)‐to‐AR and AR‐to‐VRBody settings. We also found that these special patterns of leadership only emerged for 3D interactions and not for 2D interactions. Results about the participants' experience of leadership, collaboration, embodiment, presence, and copresence shed further light on these findings.

We present a low-cost solution for yaw drift in head-mounted display systems that performs better than current commercial solutions and provides a wide capture area for pose tracking. Our method applies an extended Kalman filter to combine marker tracking data from an overhead camera with onboard head-mounted display accelerometer readings. To achieve low latency, we accelerate marker tracking with color blob localisation and perform this computation on the camera server, which only transmits essential pose data over WiFi for an unencumbered virtual reality system.

The most common approach to automatic summarization and highlight detection in sports video is to train an automatic classifier to detect semantic highlights based on occurrences of low-level features such as action replays, excited commentators or changes in a scoreboard. We propose an alternative approach based on the detection of perception concepts (PCs) and the construction of Petri-Nets, which can be used for both semantic description and event detection within sports videos. Low-level algorithms to detect PCs using visual, aural and motion characteristics are proposed, and a series of Petri-Nets composed of PCs is formally defined to describe video content. We call this a perception concept network–Petri-Net (PCN–PN) model. Using PCN–PNs, personalized high-level semantic descriptions of video highlights can be facilitated and queries on high-level semantics can be achieved. A particular strength of this framework is that we can easily build semantic detectors based on PCN–PNs to search within sports videos and locate interesting events. Experimental results based on recorded sports video data across three types of sports games (soccer, basketball and rugby), and each from multiple broadcasters, are used to illustrate the potential of this framework.

In current systems for browsing image collections, users are presented with sets of thumbnail images arranged in some default order on the screen. We are investigating whether it benefits users to have sets of thumbnails arranged according to their mutual similarity, so images that are alike are placed together. There are, of course, many possible definitions of "similarity": so far we have explored measurements based on low-level visual features, and on the textual captions assigned to the images. Here we describe two experiments, both involving designers as the participants, examining whether similarity-based arrangements of the candidate images are helpful for a picture selection task. Firstly, the two types of similarity-based arrangement were informally compared. Then, an arrangement based on visual similarity was more formally compared with a control of a random arrangement. We believe this work should be of interest to anyone designing a system that involves presenting sets of images to users. Keywords Image retrieval, information visualisation, evaluation.

This paper shows that the structure of the isobrightness contours in 'smooth' regions of a segmented image may be used to quantify the variation in shading. Topographic terms are then appropriate for labelling the kinds of generic structure that arise in smooth region domes, bowls, ridges, valleys, slopes and folds are quantifiable. The method uses contour context rather that filter banks or a solution to the shape from shading problem to quality the form of a region's brightness function. Region segmentation (distinguishing smooth from textured regions) is also performed with a largely filter free segmentation scheme with a brief outline of the scheme being given.

No abstract available.

This paper derives what we term the Euclidean hinge constraint for projective reconstruction of objects displaying articulated motion. A Euclidean hinge is defined here to be an articulation axis with the proviso that any plane perpendicular to the articulation axis in link 1 has a coincident plane which is perpendicular to the articulation ads in link 2 and that these planes remain coincident under articulated motion. This constraint permits the independent projective reconstructions of two adjacent articulated links to be placed in a common frame. The constraint may be expressed mathematically by considering what we define as circular parallax. Additionally the existence of a Euclidean hinge permits the permits the projective frame to be brought nearer to a Euclidean frame for the reconstructed object. A brief reprise of the method of articulation axis estimation is given together with a more extensive series of experimental results.

This paper derives what we term the Euclidean hinge constraint for projective reconstruction of objects displaying articulated motion. A Euclidean hinge is defined here to be an articulation axis with the proviso that any plane perpendicular to the articulation axis in link 1 has a coincident plane which is perpendicular to the articulation axis in link 2, and that these planes remain coincident under articulated motion. This constraint permits the independent projective reconstructions of two adjacent articulated links to be placed in a common frame. The constraint may be expressed mathematically by considering what we define as circular parallax. Additionally, the existence of a Euclidean hinge permits the projective frame to be brought nearer to a Euclidean frame for the reconstructed object.

This paper presents a novel hierarchical cluster based texture model. The method first estimates a code-book for micro-texture in pixel neighbourhoods using a variant of Bezdek's fuzzy c-mean clustering routine. The elements of the code-book are then used to "represent" the image. Larger scale textural variations are found by performing grouping over code-book elements in the "represented" image. At this stage a dispersed non-compact neighbourhood together with a c-medioid clustering method are used. The model falls into the class of structural texture models and depends on the multiple re-occurrence of micro-texture to function. The model is able to distinguish between Brodatz textures and detect "faults" in regular textures.

This paper presents a method for doing motion segmentation for autonomous vehicles which drive on planar surfaces. There are two distinct types of independent motion that may occur within an image sequence taken from a moving vehicle. The first generic type of independent motion is when the projected motion of points on the independent object violate the epipolar constraint. The second case is where the epipolar constraint is not violated. This paper demonstrates that it is possible to detect this second type of independent motion by looking for progressive dis-occlusion of the road. A novel collision prediction method is also given. The method predicts the projection of a corridor down which the AGV will travel. This prediction may be used for time to contact collision prediction and the corridor width embodies an estimate of the vehicles size.>

This paper presents an algorithm for transforming closed planar curves into a canonical form, independent of the viewpoint from which the original image of the contour was taken. The transformation that takes the contour to its canonical form is a member of the projective group PGL(2), chosen because PGL(2) contains all possible transformations of a plane curve under central projection onto another plane. The scheme relies on solving computationally an "isoperimetric" problem in which a transformation is sought which maximises the area of a curve given unit perimeter. In the case that the transformation is restricted to the affine subgroup there is a unique extremising transformation for any piecewise smooth closed curve. Uniqueness holds, almost always, even for curves that are not closed. In the full projective case, isoperimetric normalization is well-defined only for closed curves. We have found computational counterexamples for which there is more than one extremal transformation. Numerical algorithms are described and demonstrated both for the affine and the projective cases. Once a canonical curve is obtained, its isoperimetric area can be regarded as an invariant descriptor of shape.>

The author presents a means of segmenting independently moving objects from rigid backgrounds and recovering the orientations of the normals of local planar surface patches. The camera motion can be arbitrary with the proviso that the independent image motion violates the epipolar constraint. The method relies on describing the motion of points in the world in terms of their angular velocity relative to the camera. The method is crucially dependent on estimating camera rotation around image directions. An assumption about the likely motion of automatic guided vehicles is used to resolve the two-fold ambiguity in the estimate of the normal of a local planar patch. This allows local scene structure and camera rotation to be estimated. Motion segmentation is demonstrated on a real image sequence.>

This paper aims to develop a simple algorithm for determining the direction of ego-motion of a monocular observer in a static environment. Rather than returning a single direction the algorithm returns a set of motion directions known to contain the true direct tion. Translational motion can be arbitrary. The algorithm is based on one invented by Horn and Weldon [1]. It uses only normal components of optical flow at discrete image locations and is only intended to function when the the contribution of rotation to the apparent motion is small. The algorithm uses the fact that imaged points must be at some positive distance from the viewer. No implicit assumptions are made about the scene being viewed. The algorithm is illustrated on an artificially generated set of normal components.