Pose-free neural radiance fields (NeRF) aim to train NeRF with unposed
m...
Neural Radiance Field (NeRF) has shown impressive performance in novel v...
Pre-training robot policies with a rich set of skills can substantially
...
Open-vocabulary segmentation of 3D scenes is a fundamental function of h...
Audio-driven talking face generation, which aims to synthesize talking f...
Facial expression editing has attracted increasing attention with the ad...
3D style transfer aims to render stylized novel views of a 3D scene with...
Quantizing images into discrete representations has been a fundamental
p...
This paper develops the structure-preserving finite volume weighted
esse...
Recently, single image super-resolution (SR) under large scaling factors...
Visual relocalization has been a widely discussed problem in 3D vision: ...
Deep generative models have achieved conspicuous progress in realistic i...
Leveraging StyleGAN's expressivity and its disentangled latent codes,
ex...
Neural Radiance Fields (NeRF) have demonstrated very impressive performa...
Exemplar-based image translation establishes dense correspondences betwe...
Perceiving the similarity between images has been a long-standing and
fu...
Transformers have been successful in many vision tasks, thanks to their
...
Recently, there have been many advances in autonomous driving society,
a...
As information exists in various modalities in real world, effective
int...
Recent years pretrained language models (PLMs) hit a success on several
...
Opacity, as an important property in information-flow security, characte...
Matching local features across images is a fundamental problem in comput...
Image super-resolution (SR) research has witnessed impressive progress t...
This paper develops a new empirical Bayesian inference algorithm for sol...
Accurate localization is fundamental to a variety of applications, such ...
Understanding the meaning of existing SQL queries is critical for code
m...
Temporal camera relocalization estimates the pose with respect to each v...
This work focuses on mitigating two limitations in the joint learning of...
The self-supervised learning of depth and pose from monocular sequences
...
Establishing correspondences between two images requires both local and
...
We introduce Spatial Group Convolution (SGC) for accelerating the comput...
Most existing studies on learning local features focus on the patch-base...
Sensing the medical scenario can ensure the safety during the surgical
o...