Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

1 code implementation • CVPR 2023 • Wenteng Liang, Feng Xue, Yihao Liu, Guofeng Zhong, Anlong Ming

The recently proposed open-world object and open-set detection have achieved a breakthrough in finding never-seen-before objects and distinguishing them from known ones.

Object object-detection +2

Monocular Depth Distribution Alignment with Low Computation

1 code implementation • 9 Mar 2022 • Fei Sheng, Feng Xue, Yicong Chang, Wenteng Liang, Anlong Ming

In this paper, we model the majority of accuracy contrast between them as the difference of depth distribution, which we call "Distribution drift".

Monocular Depth Estimation

Fast Road Segmentation via Uncertainty-aware Symmetric Network

1 code implementation • 9 Mar 2022 • Yicong Chang, Feng Xue, Fei Sheng, Wenteng Liang, Anlong Ming

The high performance of RGB-D based road segmentation methods contrasts with their rare application in commercial autonomous driving, which is owing to two reasons: 1) the prior methods cannot achieve high inference speed and high accuracy in both ways; 2) the different properties of RGB and depth data are not well-exploited, limiting the reliability of predicted road.

Autonomous Driving Road Segmentation

MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment

1 code implementation • 2 Dec 2021 • Jie Ren, Wenteng Liang, Ran Yan, Luo Mai, Shiwen Liu, Xiao Liu

Large-scale Bundle Adjustment (BA) requires massive memory and computation resources which are difficult to be fulfilled by existing BA libraries.