We present EgoHumans, a new multi-view multi-human video benchmark to ad...
We present Neural Pixel Composition (NPC), a novel approach for continuo...
Image-based volumetric avatars using pixel-aligned features promise
gene...
We present a novel neural implicit representation for articulated human
...
Recent neural view synthesis methods have achieved impressive quality an...
We present streaming self-training (SST) that aims to democratize the pr...
We present simple video-specific autoencoders that enables human-control...
We present a case-study to improve the task-specific representation by
l...
We present a data-driven approach for 4D space-time visualization of dyn...
We present an unsupervised approach that enables us to convert the speec...
We introduce a data-driven approach for interactively synthesizing
in-th...
We introduce a data-driven approach for unsupervised video retargeting t...
We present a simple approach based on pixel-wise nearest neighbors to
un...
We present a simple nearest-neighbor (NN) approach that synthesizes
high...
In this work, we show that saturating output activation functions, such ...
We explore design principles for general pixel-level prediction problems...
We explore architectures for general pixel-level prediction problems, fr...
We introduce an approach that leverages surface normal predictions, alon...
Building on the success of recent discriminative mid-level elements, we
...