Keyan Chen

• Doctor of Engineering
• PhD Student at Beihang University

The advancement of remote sensing technology has improved the spatial resolution of satellite imagery, facilitating more detailed visual representations for diverse interpretations. However, existing methods exhibit limited generalization capabilities across varied applications. While some contemporary foundation models demonstrate potential, they...

Remote sensing novel view synthesis (NVS) offers significant potential for 3D interpretation of remote sensing scenes, with important applications in urban planning and environmental monitoring. However, remote sensing scenes frequently lack sufficient multi-view images due to acquisition constraints. While existing NVS methods tend to overfit when...

Remote sensing image super-resolution (SR) aims to reconstruct high-resolution remote sensing images from low-resolution inputs, thereby addressing limitations imposed by sensors and imaging conditions. However, the inherent characteristics of remote sensing images, including diverse ground object types and complex details, pose significant challen...

Referring remote sensing image segmentation is crucial for achieving fine-grained visual understanding through free-format textual input, enabling enhanced scene and object extraction in remote sensing applications. Current research primarily utilizes pre-trained language models to encode textual descriptions and align them with visual modalities,...

Remote sensing image semantic change detection is a method used to analyze remote sensing images, aiming to identify areas of change as well as categorize these changes within images of the same location taken at different times. Traditional change detection methods often face challenges in generalizing across semantic categories in practical scena...

Generative foundation models have advanced large-scale text-driven natural image generation, becoming a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on large-scale text-to-image (text2image) generation technology. Existing remote sensing image-text datasets are sma...

The segmentation and interpretation of the Martian surface play a pivotal role in Mars exploration, providing essential data for the trajectory planning and obstacle avoidance of rovers. However, the complex topography, self-similar surface features, and the lack of extensive annotated data pose significant challenges to the high-precision semantic...

We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training expenses and often struggle with generalization to unseen images. To this end, we introduce a fully modularized frame...

Recently, the Mamba architecture based on state space models has demonstrated remarkable performance in a series of natural language processing tasks and has been rapidly applied to remote sensing change detection (CD) tasks. However, most methods enhance the global receptive field by directly modifying the scanning mode of Mamba, neglecting the cr...

Remote sensing image super-resolution (SR) aims to reconstruct high-resolution remote sensing images from low-resolution inputs, thereby addressing limitations imposed by sensors and imaging conditions. However, the inherent characteristics of remote sensing images, including diverse ground object types and complex details, pose significant challen...

Recently, generative foundation models (GFMs) have significantly advanced large-scale text-driven natural image generation and become a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on large-scale text-to-image (text2image) generation technology. Existing remote sen...

Temporal image analysis in remote sensing has traditionally centered on change detection, which identifies regions of change between images captured at different times. However, change detection remains limited by its focus on visual-level interpretation, often lacking contextual or descriptive information. The rise of Vision-Language Models (VLMs)...

Many existing adversarial attacks generate $L_{p}$ -norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards visual imperceptibility, some recent works explore unrestricted attacks without $L_{p}$ -norm constraints, y...

We present Open-CD, a change detection toolbox that contains a rich set of change detection methods as well as related components and modules. The toolbox started from a series of open source general vision task tools, including OpenMMLab Toolkits, PyTorch Image Models, etc. It gradually evolves into a unified platform that covers many popular chan...

Remote sensing image change captioning (RSICC) aims to articulate the changes in objects of interest within bi-temporal remote sensing images using natural language. Given the limitations of current RSICC methods in expressing general features across multi-temporal and spatial scenarios, and their deficiency in providing granular, robust, and preci...

Recently, the Mamba architecture based on state space models has demonstrated remarkable performance in a series of natural language processing tasks and has been rapidly applied to remote sensing change detection (CD) tasks. However, most methods enhance the global receptive field by directly modifying the scanning mode of Mamba, neglecting the cr...

Novel View Synthesis (NVS) is an important task for 3D interpretation in remote sensing scenes, which also benefits vicinagearth security by enhancing situational awareness capabilities. Recently, NVS methods based on Neural Radiance Fields (NeRFs) have attracted increasing attention for self-supervised training and highly photo-realistic synthesis...

Deep neural networks have been widely applied in remote sensing, and the research on its adversarial attack algorithm is the key to evaluating its robustness. Current adversarial attack methods primarily prioritize maximizing the attack success rate, disregarding the imperceptibility of the generated adversarial noise to human visual perception. Mo...

Leveraging the extensive training data from SA-1B, the Segment Anything Model (SAM) demonstrates remarkable generalization and zero-shot capabilities. However, as a category-agnostic instance segmentation method, SAM heavily relies on prior manual guidance, including points, boxes, and coarse-grained masks. Furthermore, its performance in remote se...

Despite the success of deep learning-based change detection (CD) methods, their existing insufficiency in temporal (channel and spatial) and multiscale alignment has rendered them insufficient capability in mitigating external factors (illumination changes and perspective differences) arising from different imaging conditions during CD. In this art...

In contrast to digital image adversarial attacks, adversarial patch attacks involve physical operations that project crafted perturbations into real-world scenarios. During the digital-to-physical transition, adversarial patches inevitably undergo information distortion. Existing approaches focus on data augmentation and printer color gamut regular...

Remote sensing image change captioning (RSICC) aims to describe surface changes between multitemporal remote sensing images in language, including the changed object categories, locations, and dynamics of changing objects (e.g., added or disappeared). This poses challenges to spatial and temporal modeling of bi-temporal features. Despite previous m...

Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation. The recent advancements of Convolutional Neural Networks (CNNs) and Transformers have markedly enhanced classification accuracy. Nonetheless, remote sensing scene classification remains a signif...

Monitoring changes in the Earth’s surface is crucial for understanding natural processes and human impacts, necessitating precise and comprehensive interpretation methodologies. Remote sensing satellite imagery offers a unique perspective for monitoring these changes, leading to the emergence of remote sensing image change interpretation (RSICI) as...

Accurately retrieving surface meteorological states at arbitrary locations is of great application significance in weather forecasting and climate modeling. Since meteorological variables are typically provided as coarse-resolution gridded fields, common methods obtain the states at a specific location directly through spatial interpolation can lea...

Cloud and snow detection in remote sensing images has advanced significantly with the aid of deep learning methods. However, deep learning methods necessitate a large quantity of labeled data, which consumes a substantial amount of human and material resources. Numerous studies have focused on weakly supervised methods to reduce the workload of ann...

Remote sensing image change captioning (RSICC) aims to articulate the changes in objects of interest within bi-temporal remote sensing images using natural language. Given the limitations of current RSICC methods in expressing general features across multi-temporal and spatial scenarios, and their deficiency in providing granular, robust, and preci...

Optical remote sensing imagery is often compromised by cloud cover, making effective cloud removal techniques essential for enhancing the usability of such data. We designed a novel structural representation-guided GAN framework for cloud removal, in which structure and gradient branches are integrated into the network, helping the model focus on t...

Recent image harmonization methods have demonstrated promising results. However, due to their heavy reliance on a large number of composite images, these works are expensive in the training phase and often fail to generalize to unseen images. In this paper, we draw lessons from human behavior and come up with a zero-shot image harmonization method....

Leveraging vast training data (SA-1B), the foundation Segment Anything Model (SAM) proposed by Meta AI Research exhibits remarkable generalization and zero-shot capabilities. Nonetheless, as a category-agnostic instance segmentation method, SAM heavily depends on prior manual guidance involving points, boxes, and coarse-grained masks. Additionally,...

Most contemporary supervised Remote Sensing (RS) image Change Detection (CD) approaches are customized for equal-resolution bitemporal images. Real-world applications raise the need for cross-resolution change detection, aka, CD based on bitemporal images with different spatial resolutions. Current cross-resolution methods that are trained with sam...

Many existing adversarial attacks generate $L_p$-norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes. Towards visual imperceptibility, some recent works explore unrestricted attacks without $L_p$-norm constraints, yet lacking...

High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly focusing on processing low-resolution (LR) images. Some recent works resort to combining with color-to-color tra...

Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Over the past two decades, we have seen a rapid technological evolution of object detection and its profound impact on the entire computer vision field. If we consider today’s object detection technique as a re...

Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly-applicable super-resolution framework called FunSR, which settles different magnifications with a unified model by exploiting context...

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario. To achieve this goal, we make the following contributions: (i) we start with a naive two-stage approach for op...

Despite its fruitful applications in remote sensing, image super-resolution (SR) is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly applicable SR framework called FunSR, which settles different magnifications with a unified model by exploiting context interacti...

High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly focusing on processing low-resolution (LR) images. Some recent works resort to combining with color-to-color tra...

Most contemporary supervised Remote Sensing (RS) image Change Detection (CD) approaches are customized for equal-resolution bitemporal images. Real-world applications raise the need for cross-resolution change detection, aka, CD based on bitemporal images with different spatial resolutions. Given training samples of a fixed bitemporal resolution di...

The rapid detection of ships within the wide sea area is essential for intelligence acquisition. Most modern deep learning-based ship detection methods focus on locating ships in high-resolution (HR) remote sensing (RS) images. Seldom efforts have been made on ship detection in medium-resolution (MR) RS images. An MR image covers a much wider area...

Fine-grained image classification can be considered as a discriminative learning process where images of different subclasses are separated from each other while the same subclass images are clustered. Most existing methods perform synchronous discriminative learning in their approaches. Although achieving promising results in fine-grained visual c...

Global land cover (GLC) products can be utilized to provide geographical supervision for remote sensing representation learning, which has significantly improved downstream tasks’ performance and decreased the demand of manual annotations. However, the time differences between remote sensing images and GLC products may introduce deviations in geogr...

Remote sensing scene classification is an important yet challenging task. In recent years, the excellent feature representation ability of Convolutional Neural Networks (CNNs) has led to substantial improvements in scene classification accuracy. However, handling resolution variations of remote sensing images is still challenging because CNNs are n...

Deep learning methods have achieved considerable progress in remote sensing image building extraction. Most building extraction methods are based on Convolutional Neural Networks (CNN). Recently, vision transformers have provided a better perspective for modeling long-range context in images, but usually suffer from high computational complexity an...

The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images. However, due to human and material resource constraints, the vast majority of remote sensing images remain unlabeled. As a result, it cannot be applied to currently available deep learning methods. To fully utilize the remaining unlabeled image...

The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images. However, due to human and material resource constraints, the vast majority of remote sensing images remain unlabeled. As a result, it cannot be applied to currently available deep learning methods. To fully utilize the remaining unlabeled image...

This paper deals with the man-machine interaction of robotic arm teleoperation by the developed Kinect and first-person-perspective follow-up technologies. Kinect is used to collect and preprocess the depth information to determine the hand position vector. With the help of the virtual robotic arm set up by Processing, the relationship between the...