Creating diverse and high-quality 3D assets with an automatic generative...
Visual tracking has made significant improvements in the past few decade...
3D human generation from 2D images has achieved remarkable progress thro...
Synthesizing physically plausible human motions in 3D scenes is a challe...
Spatial convolutions are extensively used in numerous deep video models....
Recent advancements in vision foundation models (VFMs) have opened up ne...
In the previous studies, the high-order gas-kinetic schemes (HGKS) have
...
Real-scanned point clouds are often incomplete due to viewpoint, occlusi...
The recent advances in camera-based bird's eye view (BEV) representation...
Motion mimicking is a foundational task in physics-based character anima...
Existing image restoration methods mostly leverage the posterior distrib...
The robustness of 3D perception systems under natural corruptions from
e...
Existing Human NeRF methods for reconstructing 3D humans typically rely ...
Recent advances in modeling 3D objects mostly rely on synthetic datasets...
With the prevalence of LiDAR sensors in autonomous driving, 3D object
tr...
3D object detection using point clouds has attracted increasing attentio...
High-order gas-kinetic scheme (HGKS) has become a workable tool for the
...
Densely annotating LiDAR point clouds is costly, which restrains the
sca...
Due to the visual ambiguity, purely kinematic formulations on monocular ...
Human-centric perception plays a vital role in vision and graphics. But ...
In this paper, a third order gas kinetic scheme is developed on the thre...
Temporal contexts among consecutive frames are far from being fully util...
In this paper, the discontinuous Galerkin based high-order gas-kinetic
s...
3D perception, especially point cloud classification, has achieved
subst...
As real-scanned point clouds are mostly partial due to occlusions and
vi...
Learning to reconstruct 3D garments is important for dressing 3D human b...
3D point cloud is an important 3D representation for capturing real worl...
In a point cloud sequence, 3D object tracking aims to predict the locati...
Point cloud registration for 3D objects is very challenging due to spars...
Chamfer Distance (CD) and Earth Mover's Distance (EMD) are two broadly
a...
In this paper, a high-order gas-kinetic scheme is developed for the equa...
Spatial convolutions are widely used in numerous deep video models. It
f...
Most 3D shape completion approaches rely heavily on partial-complete sha...
Real-scanned point clouds are often incomplete due to viewpoint, occlusi...
Accurate 6D object pose estimation is fundamental to robotic manipulatio...
In this paper, a simple and efficient third-order weighted essentially
n...
Motivated by the success of encoding multi-scale contextual information ...