Camera localization in 3D LiDAR maps has gained increasing attention due...
This paper presents a novel approach to computing vector road maps from
...
The robustness of object detection models is a major concern when applie...
Event-based motion deblurring has shown promising results by exploiting
...
Existing adversarial attacks against Object Detectors (ODs) suffer from ...
The primal sketch is a fundamental representation in Marr's vision theor...
Defocus blur detection (DBD) separates in-focus and out-of-focus regions...
The detection of flooded areas using high-resolution synthetic aperture ...
Current semantic segmentation models have achieved great success under t...
Instance segmentation of point clouds is a crucial task in 3D field with...
Detecting arbitrarily oriented tiny objects poses intense challenges to
...
Scene Dynamic Recovery (SDR) by inverting distorted Rolling Shutter (RS)...
This paper aims at demystifying a single motion-blurred image with event...
This paper aims to develop an accurate 3D geometry representation of
sat...
Super-Resolution from a single motion Blurred image (SRB) is a severely
...
As few-shot object detectors are often trained with abundant base sample...
The tilted viewing nature of the off-nadir aerial images brings severe
c...
Although synthetic aperture imaging (SAI) can achieve the seeing-through...
This paper studies the challenging two-view 3D reconstruction in a rigor...
This paper presents a neural incremental Structure-from-Motion (SfM)
app...
Making line segment detectors more reliable under motion blurs is one of...
This paper presents Holistically-Attracted Wireframe Parsing (HAWP) for ...
Unmanned aerial vehicles (UAVs) are widely applied for purposes of
inspe...
Unmanned aerial vehicles (UAVs) are now widely applied to data acquisiti...
Deep learning-based algorithms have seen a massive popularity in differe...
High-resolution satellite images can provide abundant, detailed spatial
...
Detecting tiny objects is one of the main obstacles hindering the develo...
This paper studies the problem of holistic 3D wireframe perception (HoW-...
This paper presents OmniCity, a new dataset for omnipotent city understa...
This paper studies the problem of polygonal mapping of buildings by tack...
Tiny object detection (TOD) in aerial images is challenging since a tiny...
The challenge of the cloud removal task can be alleviated with the aid o...
Aerial scene classification remains challenging as: 1) the size of key
o...
Extracting building footprints from aerial images is essential for preci...
Modern object detectors have achieved impressive progress under the clos...
Given two point sets, the problem of registration is to recover a
transf...
Given an aerial image, aerial scene parsing (ASP) targets to interpret t...
Zero-shot semantic segmentation (ZS3) aims to segment the novel categori...
Targeting at depicting land covers with pixel-wise semantic categories,
...
In this paper, we propose an end-to-end learning framework for event-bas...
This paper presents a method of learning Local-GlObal Contextual Adaptat...
This paper tackles the problem of table structure parsing (TSP) from ima...
This report summarizes the results of Learning to Understand Aerial Imag...
This paper presents a neural network built upon Transformers, namely Pla...
Recently, object detection in aerial images has gained much attention in...
Recently, deep learning based methods have demonstrated promising result...
Unsupervised representation learning achieves promising performances in
...
Synthetic aperture imaging (SAI) is able to achieve the see through effe...
In the past decade, object detection has achieved significant progress i...
Semantic segmentation for aerial platforms has been one of the fundament...