We propose a novel method that renders point clouds as if they are surfa...
Recent works on 3D reconstruction from posed images have demonstrated th...
We propose a generative framework, FaceLit, capable of generating a 3D f...
The recent amalgamation of transformer and convolutional designs has led...
Synthesizing natural head motion to accompany speech for an embodied
con...
Recent isotropic networks, such as ConvMixer and vision transformers, ha...
Efficient neural network backbones for mobile devices are often optimize...
Photorealistic rendering and reposing of humans is important for enablin...
When deploying deep learning models to a device, it is traditionally ass...
Despite the recent success in many applications, the high computational
...
To detect bias in face recognition networks, it can be useful to probe a...
Photo-realistic visualization and animation of expressive human faces ha...
The optical flow of humans is well known to be useful for the analysis o...
Deep neural nets achieve state-of-the-art performance on the problem of
...
Three-dimensional human body models are widely used in the analysis of h...
Three-dimensional human body models are widely used in the analysis of h...
Audio-driven 3D facial animation has been widely explored, but achieving...
Learned 3D representations of human faces are useful for computer vision...
The optical flow of humans is well known to be useful for the analysis o...
We address the unsupervised learning of several interconnected problems ...
We learn to compute optical flow by combining a classical spatial-pyrami...