A key challenge of learning the geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D human reconstruction when applying to real-world imager
y. We address this challenge by leveraging a new data resource: a number of social media dance videos that span diverse appearance, clothing styles, performances, and identities. Each video depicts dynamic movements of the body and clothes of a single person while lacking the 3D ground truth geometry. To utilize these videos, we present a new method to use the local transformation that warps the predicted local geometry of the person from an image to that of another image at a different time instant. This allows self-supervision as enforcing a temporal coherence over the predictions. In addition, we jointly learn the depth along with the surface normals that are highly responsive to local texture, wrinkle, and shade by maximizing their geometric consistency. Our method is end-to-end trainable, resulting in high fidelity depth estimation that predicts fine geometry faithful to the input real image. We demonstrate that our method outperforms the state-of-the-art human depth estimation and human shape recovery approaches on both real and rendered images.
In this paper, we investigate upper and lower bounds on the capacity of two-user fading broadcast channels where one of the users has a constant (non-fading) channel. We use the Costa entropy power inequality (EPI) along with an optimization framewor
k to derive upper bounds on the sum-capacity and superposition coding to obtain lower bounds on the sum-rate for this channel. For this fading broadcast channel where one channel is constant, we find that the upper and lower bounds meet under special cases, and in general, we show that the achievable sum-rate comes within a constant of the outer bound.
