Related papers: EarthBridge: A Solution for 4th Multi-modal Aerial…
The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image. Although significant progress has been made by deep learning models, they are trained on synthetic paired…
Referring remote sensing image segmentation (RRSIS) enables the precise delineation of regions within remote sensing imagery through natural language descriptions, serving critical applications in disaster response, urban development, and…
We approach instantaneous mapping, converting images to a top-down view of the world, as a translation problem. We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or…
In remote sensing, we are interested in modeling various modalities for some geographic location. Several works have focused on learning the relationship between a location and type of landscape, habitability, audio, textual descriptions,…
In the domain of scientific imaging, interpreting visual data often demands an intricate combination of human expertise and deep comprehension of the subject materials. This study presents a novel methodology to linguistically emulate and…
Bird's-eye-view (BEV) images have been widely demonstrated to provide valuable prior information for navigation. Given the global information provided by such views, two key challenges remain: how to fully exploit this information and how…
Synthetic Aperture Radar (SAR) imagery provides robust environmental and temporal coverage (e.g., during clouds, seasons, day-night cycles), yet its noise and unique structural patterns pose interpretation challenges, especially for…
Integrating multispectral data in object detection, especially visible and infrared images, has received great attention in recent years. Since visible (RGB) and infrared (IR) images can provide complementary information to handle light…
Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…
Diffusion models have achieved remarkable progress on image-to-video (I2V) generation, while their noise-to-data generation process is inherently mismatched with this task, which may lead to suboptimal synthesis quality. In this work, we…
We present the Transparent Earth, a transformer-based architecture for reconstructing subsurface properties from heterogeneous datasets that vary in sparsity, resolution, and modality, where each modality represents a distinct type of…
Unmanned Aerial Vehicles (UAVs) are transforming infrastructure inspections in the Architecture, Engineering, Construction, and Facility Management (AEC+FM) domain. By synthesizing insights from over 150 studies, this review paper…
Cross-spectrum depth estimation aims to provide a depth map in all illumination conditions with a pair of dual-spectrum images. It is valuable for autonomous vehicle applications when the vehicle is equipped with two cameras of different…
Traditional vision-based material perception methods often experience substantial performance degradation under visually impaired conditions, thereby motivating the shift toward non-visual multimodal material perception. Despite this,…
Remote sensing composed image retrieval (RSCIR) enables search in large satellite image archives using composed queries that combine a reference image with a textual modifier. Although RSCIR offers a flexible interface for expressing…
Background: Deep learning has significantly advanced medical image analysis, with Vision Transformers (ViTs) offering a powerful alternative to convolutional models by modeling long-range dependencies through self-attention. However, ViTs…
We present a mutual information-based framework for unsupervised image-to-image translation. Our MCMI approach treats single-cycle image translation models as modules that can be used recurrently in a multi-cycle translation setting where…
We propose and investigate an "interface-flattening" transformation, hinging upon Transformation Optics (T.O.) techniques, to facilitate the rigorous analysis of electromagnetic (EM) fields radiated by sources embedded in tilted,…
Change detection (CD) in remote sensing aims to identify semantic differences between satellite images captured at different times. While deep learning has significantly advanced this field, existing approaches based on convolutional neural…
Composed image retrieval (CIR) requires multi-modal models to jointly reason over visual content and semantic modifications presented in text-image input pairs. While current CIR models achieve strong performance on common benchmark cases,…