We investigate the use of Neural Radiance Fields (NeRF) to learn high qu...
We present Mobile Video Networks (MoViNets), a family of computation and...
Accurate modeling of 3D objects exhibiting transparency, reflections and...
Ensembling is a simple and popular technique for boosting evaluation
per...
Object frequency in the real world often follows a power law, leading to...
Federated Learning enables visual models to be trained on-device, bringi...
Autonomous drone racing is a challenging research problem at the interse...
Federated Learning enables visual models to be trained in a
privacy-pres...
We present Contingency Model Predictive Control (CMPC), a novel and
impl...
Yes, it can. Data augmentation is perhaps the oldest preprocessing step ...
This paper presents a weakly-supervised approach to object instance
segm...
Recent advances in video super-resolution have shown that convolutional
...
Human vision is able to immediately recognize novel visual categories af...
Deep reinforcement learning yields great results for a large array of
pr...
Human keypoints are a well-studied representation of people.We explore h...
In this paper we present a dense ground truth dataset of nonrigidly defo...
It is hard to densely track a nonrigid object in long term, which is a
f...
This paper investigates the connections between two state of the art
cla...