To address these difficulties, we propose a method to build an animatable clothed body avatar with an explicit representation of the clothing on the upper body from multi-view captured videos.
The core intuition behind our method is that better drivability and generalization can be achieved by disentangling the driving signals and remaining generative factors, which are not available during animation.
A differentiable renderer is utilized to align our captured shapes to the input frames by minimizing the difference in both silhouette, segmentation, and texture.
Extensive experiments in several typical lifelong learning scenarios demonstrate that our method outperforms the state-of-the-art methods in both accuracies on new tasks and performance preservation on old tasks.
Federated learning (FL) enables on-device training over distributed networks consisting of a massive amount of modern smart devices, such as smartphones and IoT (Internet of Things) devices.
Using trace-driven and real-world experiments, we demonstrate significant improvements of Comyco's sample efficiency in comparison to prior work, with 1700x improvements in terms of the number of samples required and 16x improvements on training time required.
Consumer depth sensors are more and more popular and come to our daily lives marked by its recent integration in the latest Iphone X.
By prioritizing stereo matching on a subset of patches that are highly reconstructable and also cover the 3D surface, we are able to accelerate MVS with minimal reduction in accuracy and completeness.