Abstract Recently, Vision Transformer (ViT) has continuously established new milestones in
the computer vision field, while the high computation and memory cost makes its …

Abstract 3D point-clouds and 2D images are different visual representations of the physical
world. While human vision can understand both representations, computer vision models …

Transformer with its underlying attention mechanism and the ability to capture long-range
dependencies makes it become a natural choice for unordered point cloud data. However …

Indoor scenes exhibit significant appearance variations due to myriad interactions between
arbitrarily diverse object shapes, spatially-changing materials, and complex lighting …

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits
feature fusion from both modalities for point-wise scene flow estimation. Previous methods …

While numerous 3D detection works leverage the complementary relationship between RGB
images and point clouds, developments in the broader framework of semi-supervised object …

A recent trend in computer vision is to replace convolutions with transformers. However, the
performance gain of transformers is attained at a steep cost, requiring GPU years and …

Current point-cloud detection methods have difficulty detecting the open-vocabulary objects
in the real world, due to their limited generalization capability. Moreover, it is extremely …

Remarkable advancements have been made recently in point cloud analysis through the
exploration of transformer architecture, but it remains challenging to effectively learn local …

Detecting dynamic objects and predicting static road information such as drivable areas and
ground heights are crucial for safe autonomous driving. Previous works studied each …