We formulate the motor system of an interactive avatar as a generative motion model that can drive the body to move through 3D space in a perpetual, realistic, controllable, and responsive manner. Although human motion generation has been extensively studied, many existing methods lack the responsiveness and realism of real human movements. Inspired by recent advances in foundation models, we propose PRIMAL, which is learned with a two-stage paradigm. In the pretraining stage, the model learns body movements from a large number of sub-second motion segments, providing a generative foundation from which more complex motions are built. This training is fully unsupervised without annotations. Given a single-frame initial state during inference, the pretrained model not only generates unbounded, realistic, and controllable motion, but also enables the avatar to be responsive to induced impulses in real time. In the adaptation phase, we employ a novel ControlNet-like adaptor to fine-tune the base model efficiently, adapting it to new tasks such as few-shot personalized action generation and spatial target reaching. Evaluations show that our proposed method outperforms state-of-the-art baselines. We leverage the model to create a real-time character animation system in Unreal Engine that feels highly responsive and natural. Code, models, and more results are available at: https://yz-cnsdqz.github.io/eigenmotion/PRIMAL

Capturing human motion in natural scenarios means moving motion capture out of the lab and into the wild. Typical approaches rely on fixed, calibrated, cameras and reflective markers on the body, significantly limiting the motions that can be captured. To make motion capture truly unconstrained, we describe the first fully autonomous outdoor capture system based on flying vehicles. We use multiple micro-aerial-vehicles(MAVs), each equipped with a monocular RGB camera, an IMU, and a GPS receiver module. These detect the person, optimize their position, and localize themselves approximately. We then develop a markerless motion capture method that is suitable for this challenging scenario with a distant subject, viewed from above, with approximately calibrated and moving cameras. We combine multiple state-of-the-art 2D joint detectors with a 3D human body model and a powerful prior on human pose. We jointly optimize for 3D body pose and camera pose to robustly fit the 2D measurements. To our knowledge, this is the first successful demonstration of outdoor, full-body, markerless motion capture from autonomous flying vehicles.

Time tracking for Mobile Broadcast Single Frequency Network (MBSFN) subframes is known to be difficult due to very long delay spread channels. These kinds of channels induce several issues, e.g., Inter Symbol Interference (ISI), Inter Carrier Interference (ICI), Channel Estimation (CE) errors, which limit the throughput performance. In this paper, we propose an approach for timing correction, estimating the frame start time (FST) that maximizes the observed SINR. In contrast to the existing literature, we include the CE error besides the ISI and ICI into the analysis. For the simplicity of analysis, we consider linear interpolation method for CE. In particular, we show that the FST based on EAP need not be the best for the system performance. Moreover, our proposed alternate frame start time yields better system performance by balancing the ISI, ICI and CE error in effect. We then extend this method taking into account the practical limitations. Using simulation, we show that the proposed algorithm provides performance gain in the range of 3–8dB over conventional methods.