Related papers: SOMA-1M: A Large-Scale SAR-Optical Multi-resolutio…
We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive…
High-resolution satellite imagery is a key element for many Earth monitoring applications. Satellites such as Sentinel-2 feature characteristics that are favorable for super-resolution algorithms such as aliasing and band-misalignment.…
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…
Due to its cloud-penetrating capability and independence from solar illumination, satellite Synthetic Aperture Radar (SAR) is the preferred data source for large-scale flood mapping, providing global coverage and including various land…
Image captioning has become an important task in computer vision, enabling models to generate natural language descriptions of visual content. While several datasets exist for natural images and high-resolution optical remote sensing…
Object extraction and segmentation from remote sensing (RS) images is a critical yet challenging task in urban environment monitoring. Urban morphology is inherently complex, with irregular objects of diverse shapes and varying scales.…
Geometric information in the normalized digital surface models (nDSM) is highly correlated with the semantic class of the land cover. Exploiting two modalities (RGB and nDSM (height)) jointly has great potential to improve the segmentation…
Drone-based multi-object tracking is essential yet highly challenging due to small targets, severe occlusions, and cluttered backgrounds. Existing RGB-based tracking algorithms heavily depend on spatial appearance cues such as color and…
We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from…
With the proliferation of low altitude unmanned aerial vehicles (UAVs), visual multi-object tracking is becoming a critical security technology, demanding significant robustness even in complex environmental conditions. However, tracking…
Synthesizing missing modalities in multi-modal magnetic resonance imaging (MRI) is vital for ensuring diagnostic completeness, particularly when full acquisitions are infeasible due to time constraints, motion artifacts, and patient…
Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g.,…
Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited…
With the advancement of drone technology, the volume of video data increases rapidly, creating an urgent need for efficient semantic retrieval. We are the first to systematically propose and study the drone video-text retrieval (DVTR) task.…
Multimodal fusion of remote sensing images serves as a core technology for overcoming the limitations of single-source data and improving the accuracy of surface information extraction, which exhibits significant application value in fields…
Recently, the diffusion-based generative paradigm has achieved impressive general image generation capabilities with text prompts due to its accurate distribution modeling and stable training process. However, generating diverse remote…
Multimodal fusion has become a key enabler for UAV-based object detection, as each modality provides complementary cues for robust feature extraction. However, due to significant differences in resolution, field of view, and sensing…
Multi-modal remote sensing images are vital for Earth observation, yet complete paired observations are often scarce in practice. Existing generative methods commonly address this problem through isolated pairwise modality translation, but…
Multimodal change detection (MMCD) identifies changed areas in multimodal remote sensing (RS) data, demonstrating significant application value in land use monitoring, disaster assessment, and urban sustainable development. However,…
Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small)…