Search Results for author:
Found 4 papers, 3 papers with code
Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving
To resolve this problem, we propose to regulate intermediate dense 3D features with the help of volume rendering.
Lidar Point Cloud Guided Monocular 3D Object Detection
We delve into this underlying mechanism and then empirically find that: concerning the label accuracy, the 3D location part in the label is preferred compared to other parts of labels.
Geometry-based Occlusion-Aware Unsupervised Stereo Matching for Autonomous Driving
Occlusion handling is a challenging problem in stereo matching, especially for unsupervised methods.
PixelLink: Detecting Scene Text via Instance Segmentation
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression.
Ranked #6 on
Scene Text Detection
on ICDAR 2013
