Remarkable progress has been made in 3D reconstruction from single-view ...
Direct optimization of interpolated features on multi-resolution voxel g...
In this paper, we propose an end-to-end framework that jointly learns
ke...
Synthetic datasets are often used to pretrain end-to-end optical flow
ne...
We show that pre-trained Generative Adversarial Networks (GANs) such as
...
Image outpainting gains increasing attention since it can generate the
c...
The exploitation of long-term information has been a long-standing probl...
In this work we develop a generalizable and efficient Neural Radiance Fi...
The diversity and complexity of degradations in real-world video
super-r...
The smart city is an emerging notion that is leveraging the Internet of
...
Transformer becomes prevalent in computer vision, especially for high-le...
We present GTT-Net, a supervised learning framework for the reconstructi...
We propose a Transformer-based framework for 3D human texture estimation...
A recurrent structure is a popular framework choice for the task of vide...
This paper reviews the first NTIRE challenge on quality enhancement of
c...
We show that pre-trained Generative Adversarial Networks (GANs), e.g.,
S...
3D human shape and pose estimation from monocular images has been an act...
Video interpolation is an important problem in computer vision, which he...
In this paper, a lightweight and accurate localization algorithm is prop...
We present a general paradigm for dynamic 3D reconstruction from multipl...
Most existing super-resolution methods do not perform well in real scena...
Most of the classical denoising methods restore clear results by selecti...