Unsupervised video object segmentation has made significant progress in
...
Monocular scene reconstruction from posed images is challenging due to t...
Most existing transformer based video instance segmentation methods extr...
Referring image segmentation aims to segment the image region of interes...
Visual relocalization has been a widely discussed problem in 3D vision: ...
3D motion estimation including scene flow and point cloud registration h...
Estimating the accurate depth from a single image is challenging since i...
Transformers have been successful in many vision tasks, thanks to their
...
State-of-the-art face recognition methods typically take the
multi-class...
Access to large and diverse computer-aided design (CAD) drawings is crit...
Modern deep-learning-based lane detection methods are successful in most...
Camera localization aims to estimate 6 DoF camera poses from RGB images....
Augmented reality (AR) has gained increasingly attention from both resea...
Accurate localization is fundamental to a variety of applications, such ...
There are increasing interests of studying the structure-from-motion (Sf...
The integration of multiple cameras and 3D Li- DARs has become basic
con...
Unsupervised person re-identification (re-ID) attractsincreasing attenti...
Deep learning based 3D shape generation methods generally utilize latent...
Previous methods on estimating detailed human depth often require superv...
In this work, we propose an end-to-end framework to learn local multi-vi...
The deep multi-view stereo (MVS) and stereo matching approaches generall...
This paper presents a neural network to estimate a detailed depth map of...
Convolutional Neural Networks (CNNs) have achieved superior performance ...
This paper presents a new training mechanism called Batch Feature Erasin...
Learned local descriptors based on Convolutional Neural Networks (CNNs) ...
Critical to the registration of point clouds is the establishment of a s...
In this paper, we tackle the accurate and consistent Structure from Moti...
We report the findings of a month-long online competition in which
parti...