Related papers: RemoteSAM: Towards Segment Anything for Earth Obse…
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…
Effective foundation modeling in remote sensing requires spatially aligned heterogeneous modalities coupled with semantically grounded supervision, yet such resources remain limited at scale. We present GeoMeld, a large-scale multimodal…
Vision-Language Models (VLMs) have demonstrated effective perception and reasoning capabilities on general-domain tasks, leading to growing interest in their application to Earth observation. However, a systematic benchmark for…
In the realm of artificial intelligence, the emergence of foundation models, backed by high computing capabilities and extensive data, has been revolutionary. Segment Anything Model (SAM), built on the Vision Transformer (ViT) model with…
This paper presents the Autonomous Driving Segment Anything Model (AD-SAM), a fine-tuned vision foundation model for semantic segmentation in autonomous driving (AD). AD-SAM extends the Segment Anything Model (SAM) with a dual-encoder and…
Quantitative remote sensing inversion aims to estimate continuous surface variables-such as biomass, vegetation indices, and evapotranspiration-from satellite observations, supporting applications in ecosystem monitoring, carbon accounting,…
Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability. However, large-scale models…
Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS) has emerged as a solution to alleviate the labeling burden…
Remote sensing images are useful for a wide variety of planet monitoring applications, from tracking deforestation to tackling illegal fishing. The Earth is extremely diverse -- the amount of potential tasks in remote sensing images is…
The Reference Remote Sensing Image Segmentation (RRSIS) task generates segmentation masks for specified objects in images based on textual descriptions, which has attracted widespread attention and research interest. Current RRSIS methods…
Large-scale foundation models in Earth Observation can learn versatile, label-efficient representations by leveraging massive amounts of unlabeled data. However, existing public datasets are often limited in scale, geographic coverage, or…
Remote sensing change captioning is an emerging and popular research task that aims to describe, in natural language, the content of interest that has changed between two remote sensing images captured at different times. Existing methods…
Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM)…
Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships beyond simple recognition tasks. In this paper, we aim to…
Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal…
Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now emerging in the Earth Observation community. These models aim to generalize across…
Remote sensing vision tasks require extensive labeled data across multiple, interconnected domains. However, current generative data augmentation frameworks are task-isolated, i.e., each vision task requires training an independent…
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…
In the rapidly advancing field of robotics, the fusion of state-of-the-art visual technologies with mobile robotic arms has emerged as a critical integration. This paper introduces a novel system that combines the Segment Anything model…
Very-High Resolution (VHR) remote sensing imagery is increasingly accessible, but often lacks annotations for effective machine learning applications. Recent foundation models like GroundingDINO and Segment Anything (SAM) provide…