Nowadays, autonomous cars can drive smoothly in ordinary cases, and it i...
Compositional neural scene graph studies have shown that radiance fields...
Test-Time Adaptation (TTA) has recently emerged as a promising approach ...
With significant annotation savings, point supervision has been proven
e...
Nowadays, many visual scene understanding problems are addressed by dens...
Large-scale radiance fields are promising mapping tools for smart
transp...
Visual re-localization aims to recover camera poses in a known environme...
Recently, 3D scenes parsing with deep learning approaches has been a hea...
Assembly sequence planning (ASP) is the essential process for modern
man...
We address the new problem of language-guided semantic style transfer of...
Detecting 3D keypoints from point clouds is important for shape
reconstr...
We study the problem of estimating room layouts from a single panorama i...
Multi-task indoor scene understanding is widely considered as an intrigu...
Accurate trajectory prediction of vehicles is essential for reliable
aut...
Semantic understanding of 3D point clouds is important for various robot...
3D scene understanding from point clouds plays a vital role for various
...
Learning from imperfect data becomes an issue in many industrial applica...
We introduce Spatial Group Convolution (SGC) for accelerating the comput...
Convolutional Neural Networks (CNNs) have become deeper and more complic...
Universal style transfer tries to explicitly minimize the losses in feat...
In this paper, we propose an alternative method to estimate room layouts...
Convolutional neural networks (CNNs) with deep architectures have
substa...