Estimating surface normals from 3D point clouds is critical for various
...
We present a lightweight post-processing method to refine the semantic
s...
Mobile stereo-matching systems have become an important part of many
app...
We present an efficient text-to-video generation framework based on late...
3D point clouds can flexibly represent continuous surfaces and can be us...
Automated video-based assessment of surgical skills is a promising task ...
Modeling the local surface geometry is challenging in 3D point cloud
und...
Learning point clouds is challenging due to the lack of connectivity
inf...
Deep learning models as an emerging topic have shown great progress in
v...
In this paper, we show our solution to the Google Landmark Recognition 2...
The attribution method provides a direction for interpreting opaque neur...
Identifying and visualizing regions that are significant for a given dee...
Lidar based 3D object detection and classification tasks are essential f...
This paper presents a novel semantic-based online extrinsic calibration
...
In this work, we introduce a novel Weighted Box Fusion (WBF) ensembling
...
Acoustic Scene Classification (ASC) is a challenging task, as a single s...
How can we edit or transform the geometric or color property of a point
...
This paper presents a novel method for detecting scene changes from a pa...
In this paper, we propose a method for cloud removal from visible light ...