Search Results for author:
Found 95 papers, 47 papers with code
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation
This work studies semantic segmentation under the domain generalization setting, where a model is trained only on the source domain and tested on the unseen target domain.
FreePoint: Unsupervised Point Cloud Instance Segmentation
Based on the point features, we perform a multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues.
Ranked #1 on
Oriented Object Detction
on DOTA 2.0
Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events
Scene Dynamic Recovery (SDR) by inverting distorted Rolling Shutter (RS) images to an undistorted high frame-rate Global Shutter (GS) video is a severely ill-posed problem due to the missing temporal dynamic information in both RS intra-frame scanlines and inter-frame exposures, particularly when prior knowledge about camera/object motions is unavailable.
Recovering Continuous Scene Dynamics from A Single Blurry Image with Events
This paper aims at demystifying a single motion-blurred image with events and revealing temporally continuous scene dynamics encrypted behind motion blurs.
Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs
This paper aims to develop an accurate 3D geometry representation of satellite images using satellite-ground image pairs.
Learning to Super-Resolve Blurry Images with Events
Super-Resolution from a single motion Blurred image (SRB) is a severely ill-posed problem due to the joint degradation of motion blurs and low spatial resolution.
Few-Shot Object Detection via Variational Feature Aggregation
As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples, the learned models are usually biased to base classes and sensitive to the variance of novel examples.
Detecting Building Changes with Off-Nadir Aerial Images
The tilted viewing nature of the off-nadir aerial images brings severe challenges to the building change detection (BCD) problem: the mismatch of the nearby buildings and the semantic ambiguity of the building facades.
Building change detection for remote sensing images
Change Detection
Learning to See Through with Events
Although synthetic aperture imaging (SAI) can achieve the seeing-through effect by blurring out off-focus foreground occlusions while recovering in-focus occluded scenes from multi-view images, its performance is often deteriorated by dense occlusions and extreme lighting conditions.
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation.
Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces
This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences.
Detecting Line Segments in Motion-blurred Images with Events
To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events.
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
At the core is a parsimonious representation that encodes a line segment using a closed-form 4D geometric vector, which enables lifting line segments in wireframe to an end-to-end trainable holistic attraction field that has built-in geometry-awareness, context-awareness and robustness.
Anomaly Detection in Aerial Videos with Transformers
In this paper, we create a new dataset, named DroneAnomaly, for anomaly detection in aerial videos.
FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification
Furthermore, the holistic features are refined by the multi-scale temporal relations in a novel fusion module for yielding more discriminative video representations.
Transformers in Remote Sensing: A Survey
Deep learning-based algorithms have seen a massive popularity in different areas of remote sensing image analysis over the past decade.
Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery
To validate the generalizability of our dataset and the proposed approach across different sensors and different geographical regions, we carry out land cover mapping on five megacities in China and six cities in other five Asian countries severally using: PlanetScope (3 m), Gaofen-1 (8 m), and Sentinel-2 (10 m) satellite images.
RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection
Then, instead of assigning samples with IoU or center sampling strategy, a new Receptive Field Distance (RFD) is proposed to directly measure the similarity between the Gaussian receptive field and ground truth.
HoW-3D: Holistic 3D Wireframe Perception from a Single Image
This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.
Accurate Polygonal Mapping of Buildings in Satellite Imagery
We addressed such an issue by exploiting the hierarchical supervision (of bottom-level vertices, mid-level line segments and the high-level regional masks) and proposed a novel interaction mechanism of feature embedding sourced from different levels of supervision signals to obtain reversible building masks for polygonal mapping of buildings.
OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
More precisely, the OmniCity contains multi-view satellite images as well as street-level panorama and mono-view images, constituting over 100K pixel-wise annotated images that are well-aligned and collected from 25K geo-locations in New York City.
Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels.
GLF-CR: SAR-Enhanced Cloud Removal with Global-Local Fusion
The challenge of the cloud removal task can be alleviated with the aid of Synthetic Aperture Radar (SAR) images that can penetrate cloud cover.
Ranked #2 on
Cloud Removal
on SEN12MS-CR
All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification
Finally, our SSF allows our framework to learn the same scene scheme from multi-grain instance representations and fuses them, so that the entire framework is optimized as a whole.
Learning to Extract Building Footprints from Off-Nadir Aerial Images
In this paper, we propose an offset vector learning scheme, which turns the building footprint extraction problem in off-nadir images into an instance-level joint prediction problem of the building roof and its corresponding "roof to footprint" offset vector.
An Empirical Study of Remote Sensing Pretraining
To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.
Ranked #1 on
Aerial Scene Classification
on UCM (80% as trainset)
Aerial Scene Classification
Building change detection for remote sensing images
+5
Revisiting Document Image Dewarping by Grid Regularization
This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization.
Expanding Low-Density Latent Regions for Open-Set Object Detection
Thus, unknown objects in low-density regions can be easily identified with the learned unknown probability.
Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration
To handle large point sets, we propose a scalable PDM algorithm by utilizing the efficient partial Wasserstein-1 (PW) discrepancy.
Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling
Finally, we perform ASP by unifying the tile-level scene classification and object-based image analysis to achieve pixel-wise semantic labeling.
Decoupling Zero-Shot Semantic Segmentation
2) a zero-shot classification task on segments.
Ranked #3 on
Open Vocabulary Semantic Segmentation
on PascalVOC-20
(hIoU metric)
Open Vocabulary Semantic Segmentation
Semantic Segmentation
+1
Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images
Targeting at depicting land covers with pixel-wise semantic categories, semantic segmentation in remote sensing images needs to portray diverse distributions over vast geographical locations, which is difficult to be achieved by the homogeneous pixel-wise forward paths in the architectures of existing deep models.
Motion Deblurring with Real Events
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency.
Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation
This paper studies the problem of multi-person pose estimation in a bottom-up fashion.
Parsing Table Structures in the Wild
In contrast to existing studies that mainly focus on parsing well-aligned tabular images with simple layouts from scanned PDF documents, we aim to establish a practical table structure parsing system for real-world scenarios where tabular input images are taken or scanned with severe deformation, bending or occlusions.
LUAI Challenge 2021 on Learning to Understand Aerial Images
This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images.
PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image.
ReDet: A Rotation-equivariant Detector for Aerial Object Detection
More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size.
Ranked #15 on
Object Detection In Aerial Images
on DOTA
Deep Graph Matching under Quadratic Constraint
Recently, deep learning based methods have demonstrated promising results on the graph matching problem, by relying on the descriptive capability of deep features extracted on graph nodes.
Ranked #4 on
Graph Matching
on Willow Object Class
Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks.
Event-based Synthetic Aperture Imaging with a Hybrid Network
Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images.
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI.
Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery
Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation.
Tiny Object Detection in Aerial Images
To build a benchmark for tiny object detection in aerial images, we evaluate the state-of-the-art object detectors on our AI-TOD dataset.
Ranked #3 on
Object Detection
on AI-TOD
3D Building Reconstruction From Monocular Remote Sensing Images
3D building reconstruction from monocular remote sensing imagery is an important research problem and an economic solution to large-scale city modeling, compared with reconstruction from LiDAR data and multi-view imagery.
Unmixing Convolutional Features for Crisp Edge Detection
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.
Ranked #2 on
Edge Detection
on MDBD
Semantic Change Detection with Asymmetric Siamese Networks
Given two multi-temporal aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries.
Mixed Noise Removal with Pareto Prior
To address this problem, we exploit the Pareto distribution as the priori of the weighting matrix, based on which an accurate and robust weight estimator is proposed for mixed noise removal.
Align Deep Features for Oriented Object Detection
However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.
Ranked #19 on
Object Detection In Aerial Images
on DOTA
Event Enhanced High-Quality Image Recovery
To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras.
Implicit Euler ODE Networks for Single-Image Dehazing
Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem.
X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing.
On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID
After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation.
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities
Considering the rapid evolution of this field, this paper provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers.
FGN: Fully Guided Network for Few-Shot Instance Segmentation
Few-shot instance segmentation (FSIS) conjoins the few-shot learning paradigm with general instance segmentation, which provides a possible way of tackling instance segmentation in the lack of abundant labeled data for training.
Zero-Assignment Constraint for Graph Matching with Outliers
Graph matching (GM), as a longstanding problem in computer vision and pattern recognition, still suffers from numerous cluttered outliers in practical applications.
Fisheye Distortion Rectification from Deep Straight Lines
This paper presents a novel line-aware rectification network (LaRecNet) to address the problem of fisheye distortion rectification based on the classical observation that straight lines in 3D space should be still straight in image planes.
Semantic Change Pattern Analysis
Change detection is an important problem in vision field, especially for aerial images.
Holistically-Attracted Wireframe Parsing
For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image.
Ranked #1 on
Line Segment Detection
on wireframe dataset
(FH metric)
Matching Neuromorphic Events and Color Images via Adversarial Learning
The event camera has appealing properties: high dynamic range, low latency, low power consumption and low memory usage, and thus provides complementariness to conventional frame-based cameras.
Plug & Play Convolutional Regression Tracker for Video Object Detection
As the tracker reuses the features from the detector, it is a very light-weighted increment to the detection network.
Learning Regional Attraction for Line Segment Detection
Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice.
Conditional Generative ConvNets for Exemplar-based Texture Synthesis
Given a texture exemplar, the cgCNN model defines a conditional distribution using deep statistics of a ConvNet, and synthesize new textures by sampling from the conditional distribution.
Gliding vertex on the horizontal bounding box for multi-oriented object detection
Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.
Ranked #40 on
Object Detection In Aerial Images
on DOTA
LIP: Learning Instance Propagation for Video Object Segmentation
In recent years, the task of segmenting foreground objects from background in a video, i. e. video object segmentation (VOS), has received considerable attention.
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances.
Ranked #1 on
Object Detection
on iSAID
Learning to Calibrate Straight Lines for Fisheye Image Rectification
This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images.
A Functional Representation for Graph Matching
In this paper, we present a functional representation for graph matching (FRGM) that aims to provide more geometric insights on the problem and reduce the space and time complexities of corresponding algorithms.
Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, Applications, and Prospects
We hope this paper will provide remote-sensing researchers an overall picture of recent UAV-based remote sensing developments and help guide the further research on this topic.
Learning Attraction Field Representation for Robust Line Segment Detection
In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained.
Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects.
Ranked #46 on
Object Detection In Aerial Images
on DOTA
GeoSay: A Geometric Saliency for Extracting Buildings in Remote Sensing Images
More precisely, given an image, the geometric saliency is derived from a mid-level geometric representations based on meaningful junctions that can locally describe geometrical structures of images.
UAVid: A Semantic Segmentation Dataset for UAV Imagery
There already exist several semantic segmentation datasets for comparison among semantic segmentation methods in complex urban scenes, such as the Cityscapes and CamVid datasets, where the side views of the objects are captured with a camera mounted on the driving car.
Texture Mixing by Interpolating Deep Statistics via Gaussian Models
More precisely, we first reveal that the statistics used in existing deep models can be unified using a stationary Gaussian scheme.
Adaptively Transforming Graph Matching
Due to an efficient Frank-Wolfe method-based optimization strategy, we can handle graphs with hundreds and thousands of nodes within an acceptable amount of time.
Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models
The main idea is to rely on deep neural networks for presenting the contextual information contained in different types of land-covers and propose a pseudo-labeling and sample selection scheme for improving the transferability of deep models.
Accurate Building Detection in VHR Remote Sensing Images using Geometric Saliency
This paper aims to address the problem of detecting buildings from remote sensing images with very high resolution (VHR).
Large-scale Land Cover Classification in GaoFen-2 Satellite Imagery
Many significant applications need land cover information of remote sensing images that are acquired from different areas and times, such as change detection and disaster monitoring.
Recent advances and opportunities in scene classification of aerial images with deep models
Scene classification is a fundamental task in interpretation of remote sensing images, and has become an active research topic in remote sensing community due to its important role in a wide range of applications.
AID++: An Updated Version of AID on Scene Classification
Aerial image scene classification is a fundamental problem for understanding high-resolution remote sensing images and has become an active research task in the field of remote sensing due to its important role in a wide range of applications.
Rotation-Sensitive Regression for Oriented Scene Text Detection
Previous methods rely on shared features for both tasks, resulting in degraded performance due to the incompatibility of the two tasks.
Ranked #13 on
Scene Text Detection
on MSRA-TD500
Learning the Synthesizability of Dynamic Texture Samples
In this paper, we investigate the synthesizability of dynamic texture samples: {\em given a dynamic texture sample, how synthesizable it is by using EDTS, and which EDTS method is the most suitable to synthesize it?}
DOTA: A Large-scale Dataset for Object Detection in Aerial Images
The fully annotated DOTA images contains $188, 282$ instances, each of which is labeled by an arbitrary (8 d. o. f.)
Ranked #50 on
Object Detection In Aerial Images
on DOTA
Deep learning in remote sensing: a review
In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with.
Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation
Over the past two decades, a large amount of research on this task has been carried out, which mainly focuses on the following three core issues: feature extraction, similarity metric and relevance feedback.
Anisotropic-Scale Junction Detection and Matching for Indoor Images
This paper presents a novel approach to junction detection and characterization that exploits the locally anisotropic geometries of a junction and estimates the scales of these geometries using an \emph{a contrario} model.
Image Stitching by Line-guided Local Warping with Global Similarity Constraint
On one hand, the line features are integrated into a local warping model through a designed weight function.
Texture Characterization by Using Shape Co-occurrence Patterns
In contrast with existing works, the proposed method not only inherits the strong ability to depict geometrical aspects of textures and the high robustness to variations of imaging conditions from the shape-based method, but also provides a flexible way to consider shape relationships and to compute high-order statistics on the tree.
AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
The goal of AID is to advance the state-of-the-arts in scene classification of remote sensing images.
Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery
In this paper, an automatic multi-feature combined (MFC) method is proposed for cloud and cloud shadow detection in GF-1 WFV imagery.
Image stitching with perspective-preserving warping
Image stitching algorithms often adopt the global transformation, such as homography, and work well for planar scenes or parallax free camera motions.
Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints
This paper presents a significant improvement for the synthesis of texture images using convolutional neural networks (CNNs), making use of constraints on the Fourier spectrum of the results.
Dense v.s. Sparse: A Comparative Study of Sampling Analysis in Scene Classification of High-Resolution Remote Sensing Imagery
The experimental results on two commonly used datasets show that dense sampling has the best performance among all the strategies but with high spatial and computational complexity, random sampling gives better or comparable results than other sparse sampling methods, like the sophisticated multi-scale key-point operators and the saliency-based methods which are intensively studied and commonly used recently.
Meaningful Objects Segmentation from SAR Images via A Multi-Scale Non-Local Active Contour Model
The segmentation of synthetic aperture radar (SAR) images is a longstanding yet challenging task, not only because of the presence of speckle, but also due to the variations of surface backscattering properties in the images.
