This paper addresses the problem of 3D referring expression comprehensio...
LiDAR-based 3D object detection is an indispensable task in advanced
aut...
3D object detection received increasing attention in autonomous driving
...
We investigate transductive zero-shot point cloud semantic segmentation ...
Vision-centric BEV perception has recently received increased attention ...
Previous works for LiDAR-based 3D object detection mainly focus on the
s...
Accurately detecting and tracking pedestrians in 3D space is challenging...
Promising performance has been achieved for visual perception on the poi...
Recently, there have been many advances in autonomous driving society,
a...
State-of-the-art methods for driving-scene LiDAR-based perception (inclu...
In Autonomous Driving (AD) systems, perception is both security and safe...
Domain adaptive semantic segmentation refers to making predictions on a
...
We present a novel method for single image depth estimation using surfac...
3D perception using sensors under vehicle industrial standard is the rig...
Holistically understanding an object and its 3D movable parts through vi...
In this paper, we propose a novel approach to convert given speech audio...
To get clear street-view and photo-realistic simulation in autonomous
dr...
We present a novel approach to detect, segment, and reconstruct complete...
Current methods for trajectory prediction operate in supervised manners,...
Omnidirectional 360 camera proliferates rapidly for autonomous robots
si...
In this paper, we propose a novel approach to reconstruct 3D human body
...
Despite the remarkable progresses made in deep-learning based depth map
...
This paper reviews the CVPR 2019 challenge on Autonomous Driving. Baidu'...
Existing LiDAR-based 3D object detectors usually focus on the single-fra...
In this paper, we present a large-scale detailed 3D face dataset, FaceSc...
Current popular online multi-object tracking (MOT) solutions apply singl...
Conventional absolute camera pose via a Perspective-n-Point (PnP) solver...
Semantic segmentation is a challenging task that needs to handle large s...
State-of-the-art stereo matching networks have difficulties in generaliz...
Depth Completion deals with the problem of converting a sparse depth map...
Deep reinforcement learning has great potential to acquire complex, adap...
Adaptive inference is a promising technique to improve the computational...
In 2D/3D object detection task, Intersection-over-Union (IoU) has been w...
Deep neural networks (DNNs) are found to be vulnerable against adversari...
This paper presents a novel framework to recover detailed human body sha...
In the stereo matching task, matching cost aggregation is crucial in bot...
Simulation systems have become an essential component in the development...
We explore the importance of spatial contextual information in human pos...
Interactive multi-agent simulation algorithms are used to compute the
tr...
Autonomous driving has attracted remarkable attention from both industry...
In this paper, we make the first attempt to build a framework to
simulta...
We present a LIDAR simulation framework that can automatically generate ...
To safely and efficiently navigate in complex urban traffic, autonomous
...
Depth prediction is one of the fundamental problems in computer vision. ...
We aim to enable a mobile robot to navigate through environments with de...
In this paper, we present a robotic navigation algorithm with natural
la...
3D point cloud generation by the deep neural network from a single image...
Confusing classes that are ubiquitous in real world often degrade perfor...
Depth estimation from a single image is a fundamental problem in compute...
We present a novel deep learning approach to synthesize complete face im...