Generating complete 360-degree panoramas from narrow field of view image...
Text-conditional diffusion models are able to generate high-fidelity ima...
We present a new generalizable NeRF method that is able to directly
gene...
Neural Radiance Field (NeRF) is a popular method in representing 3D scen...
The recently developed discrete diffusion models perform extraordinarily...
Some group activities, such as team sports and choreographed dances, inv...
PICNet pioneered the generation of multiple and diverse results for imag...
Image translation and manipulation have gain increasing attention along ...
The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) wit...
Although much progress has been made in visual emotion recognition,
rese...
We present a neural-based model for relighting a half-body portrait imag...
Existing scene understanding systems mainly focus on recognizing the vis...
We propose a novel spatially-correlative loss that is simple, efficient ...
Bridging distant context interactions is important for high quality imag...
Automatic facial action unit (AU) recognition has attracted great attent...
While the problem of estimating shapes and diffuse reflectances of human...
In this paper, we propose a generative framework that unifies depth-base...
Facial action unit (AU) detection in the wild is a challenging problem, ...
Most image completion methods produce only one result for each masked in...
Previous spatial-temporal action localization methods commonly follow th...
Teleconference or telepresence based on virtual reality (VR) headmount
d...
Current methods for single-image depth estimation use training datasets ...
Employing deep learning-based approaches for fine-grained facial express...
We introduce a novel robust hybrid 3D face tracking framework from RGBD ...