Search Results for author: Naoto Yokoya

Found 64 papers, 32 papers with code

DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding

no code implementations27 May 2025 Weihao Xuan, Junjue Wang, Heli Qi, Zihang Chen, Zhuo Zheng, Yanfei Zhong, Junshi Xia, Naoto Yokoya

Multimodal large language models have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains limited, primarily focusing on single-temporal or bi-temporal imagery.

Benchmarking Change Detection +2

Enhancing Monocular Height Estimation via Sparse LiDAR-Guided Correction

no code implementations11 May 2025 Jian Song, Hongruixuan Chen, Naoto Yokoya

Recently, models trained on synthetic data and refined through domain adaptation have shown remarkable performance in MHE, yet it remains unclear how these models make predictions or how reliable they truly are.

Domain Adaptation

Joint Super-Resolution and Segmentation for 1-m Impervious Surface Area Mapping in China's Yangtze River Economic Belt

no code implementations8 May 2025 Jie Deng, Danfeng Hong, Chenyu Li, Naoto Yokoya

We propose a novel joint framework by integrating super-resolution and segmentation, called JointSeg, which enables the generation of 1-meter ISA maps directly from freely available Sentinel-2 imagery.

Super-Resolution

SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding

1 code implementation4 Apr 2025 Yimin Wei, Aoran Xiao, Yexian Ren, Yuting Zhu, Hongruixuan Chen, Junshi Xia, Naoto Yokoya

Synthetic Aperture Radar (SAR) is a crucial remote sensing technology, enabling all-weather, day-and-night observation with strong surface penetration for precise and continuous environmental monitoring and analysis.

Language Modeling Language Modelling +1

A Vision Centric Remote Sensing Benchmark

no code implementations20 Mar 2025 Abduljaleel Adejumo, Faegheh Yeganli, Clifford Broni-Bediako, Aoran Xiao, Naoto Yokoya, Mennatullah Siam

Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks but their remote sensing (RS) counterpart are relatively under explored.

Question Answering Representation Learning +2

MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration

1 code implementation12 Mar 2025 Zhehui Wu, Yong Chen, Naoto Yokoya, wei he

In this paper, we propose MP-HSIR, a novel multi-prompt framework that effectively integrates spectral, textual, and visual prompts to achieve universal HSI restoration across diverse degradation types and intensities.

Spectral Reconstruction

OpenEarthMap-SAR: A Benchmark Synthetic Aperture Radar Dataset for Global High-Resolution Land Cover Mapping

no code implementations18 Jan 2025 Junshi Xia, Hongruixuan Chen, Clifford Broni-Bediako, Yimin Wei, Jian Song, Naoto Yokoya

To bridge this gap and facilitate advancements in SAR-based geospatial analysis, we introduce OpenEarthMap-SAR, a benchmark SAR dataset, for global high-resolution land cover mapping.

Disaster Response Semantic Segmentation

Neural Hierarchical Decomposition for Single Image Plant Modeling

no code implementations CVPR 2025 Zhihao Liu, Zhanglin Cheng, Naoto Yokoya

Obtaining high-quality, practically usable 3D models of biological plants remains a significant challenge in computer vision and graphics.

CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation

1 code implementation30 Oct 2024 Ziyang Gong, Zhixiang Wei, Di Wang, Xianzheng Ma, Hongruixuan Chen, Yuru Jia, Yupeng Deng, Zhenming Ji, Xiangwei Zhu, Naoto Yokoya, Jing Zhang, Bo Du, Liangpei Zhang

The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios.

Domain Generalization Segmentation +1

Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmark

1 code implementation17 Sep 2024 Clifford Broni-Bediako, Junshi Xia, Jian Song, Hongruixuan Chen, Mennatullah Siam, Naoto Yokoya

While previous datasets and benchmarks discussed the few-shot segmentation setting in remote sensing, we are the first to propose a generalized few-shot segmentation benchmark for remote sensing.

Generalized Few-Shot Semantic Segmentation Segmentation +1

GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting

1 code implementation21 Aug 2024 Wanshui Gan, Fang Liu, Hongbin Xu, Ningkai Mo, Naoto Yokoya

We introduce GaussianOcc, a systematic method that investigates the two usages of Gaussian splatting for fully self-supervised and efficient 3D occupancy estimation in surround views.

Representation Learning

Segment Anything with Multiple Modalities

1 code implementation17 Aug 2024 Aoran Xiao, Weihao Xuan, Heli Qi, Yun Xing, Naoto Yokoya, Shijian Lu

It addresses three main challenges: 1) adaptation toward diverse non-RGB sensors for single-modal processing, 2) synergistic processing of multi-modal data via sensor fusion, and 3) mask-free training for different downstream tasks.

Segmentation Sensor Fusion

SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery

1 code implementation26 Jun 2024 Jian Song, Hongruixuan Chen, Weihao Xuan, Junshi Xia, Naoto Yokoya

To further enhance its utility, we develop a novel multi-task unsupervised domain adaptation (UDA) method, RS3DAda, coupled with our synthetic dataset, which facilitates the RS-specific transition from synthetic to real scenarios for land cover mapping and height estimation tasks, ultimately enabling global monocular 3D semantic understanding based on synthetic data.

Earth Observation Synthetic Data Generation +1

Local-to-Global Cross-Modal Attention-Aware Fusion for HSI-X Semantic Segmentation

no code implementations25 Jun 2024 Xuming Zhang, Naoto Yokoya, Xingfa Gu, Qingjiu Tian, Lorenzo Bruzzone

The FEM is used to enhance complementary information by combining the feature from the other modality across direction-aware, position-sensitive, and channel-wise dimensions.

Decoder Semantic Segmentation

HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model

1 code implementation17 Jun 2024 Di Wang, Meiqi Hu, Yao Jin, Yuchun Miao, Jiaqi Yang, Yichu Xu, Xiaolei Qin, Jiaqi Ma, Lingyu Sun, Chenxing Li, Chuan Fu, Hongruixuan Chen, Chengxi Han, Naoto Yokoya, Jing Zhang, Minqiang Xu, Lin Liu, Lefei Zhang, Chen Wu, Bo Du, DaCheng Tao, Liangpei Zhang

Accurate hyperspectral image (HSI) interpretation is critical for providing valuable insights into various earth observation-related applications such as urban planning, precision agriculture, and environmental monitoring.

Computational Efficiency Earth Observation +1

Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping

1 code implementation23 Apr 2024 Clifford Broni-Bediako, Junshi Xia, Naoto Yokoya

Thus, we proposed a simple yet effective framework to search for lightweight neural networks automatically for land cover mapping tasks under domain shifts.

Neural Architecture Search Unsupervised Domain Adaptation

ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model

1 code implementation4 Apr 2024 Hongruixuan Chen, Jian Song, Chengxi Han, Junshi Xia, Naoto Yokoya

Convolutional neural networks (CNN) and Transformers have made impressive progress in the field of remote sensing change detection (CD).

Attribute Building Damage Assessment +3

Change Detection Between Optical Remote Sensing Imagery and Map Data via Segment Anything Model (SAM)

no code implementations17 Jan 2024 Hongruixuan Chen, Jian Song, Naoto Yokoya

In this study, we explore unsupervised multimodal change detection between two key remote sensing data sources: optical high-resolution imagery and OpenStreetMap (OSM) data.

Change Detection Segmentation

Submeter-level Land Cover Mapping of Japan

no code implementations19 Nov 2023 Naoto Yokoya, Junshi Xia, Clifford Broni-Bediako

Deep learning has shown promising performance in submeter-level mapping tasks; however, the annotation cost of submeter-level imagery remains a challenge, especially when applied on a large scale.

Land Cover Classification

SpectralGPT: Spectral Remote Sensing Foundation Model

1 code implementation13 Nov 2023 Danfeng Hong, Bing Zhang, Xuyang Li, YuXuan Li, Chenyu Li, Jing Yao, Naoto Yokoya, Hao Li, Pedram Ghamisi, Xiuping Jia, Antonio Plaza, Paolo Gamba, Jon Atli Benediktsson, Jocelyn Chanussot

The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner.

Change Detection model +4

Enhancing Monocular Height Estimation from Aerial Images with Street-view Images

no code implementations3 Nov 2023 Xiaomou Hou, Wanshui Gan, Naoto Yokoya

Accurate height estimation from monocular aerial imagery presents a significant challenge due to its inherently ill-posed nature.

Flooding Regularization for Stable Training of Generative Adversarial Networks

no code implementations1 Nov 2023 Iu Yahiro, Takashi Ishida, Naoto Yokoya

One of the main approaches to address this problem is to modify the loss function, often using regularization terms in addition to changing the type of adversarial losses.

Image Generation

Exchange means change: an unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange

1 code implementation1 Oct 2023 Hongruixuan Chen, Jian Song, Chen Wu, Bo Du, Naoto Yokoya

Change detection (CD) is a critical task in studying the dynamics of ecosystems and human activities using multi-temporal remote sensing images.

Change Detection Image Enhancement +1

Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing

no code implementations12 Sep 2023 Clifford Broni-Bediako, Junshi Xia, Naoto Yokoya

With the success of efficient deep learning methods (i. e., efficient deep neural networks) for real-time semantic segmentation in computer vision, researchers have adopted these efficient deep neural networks in remote sensing image analysis.

Image Segmentation Real-Time Semantic Segmentation +2

SyntheWorld: A Large-Scale Synthetic Dataset for Land Cover Mapping and Building Change Detection

1 code implementation5 Sep 2023 Jian Song, Hongruixuan Chen, Naoto Yokoya

However, when it comes to remote sensing image processing, the creation of synthetic datasets becomes challenging due to the demand for larger-scale and more diverse 3D models.

Change Detection Diversity

Understanding Dark Scenes by Contrasting Multi-Modal Observations

1 code implementation23 Aug 2023 Xiaoyu Dong, Naoto Yokoya

Experiments show that our approach can effectively enhance dark scene understanding based on multi-modal images with limited semantics by shaping semantic-discriminative feature spaces.

Contrastive Learning Scene Understanding +1

A Simple Framework for 3D Occupancy Estimation in Autonomous Driving

1 code implementation17 Mar 2023 Wanshui Gan, Ningkai Mo, Hongbin Xu, Naoto Yokoya

In this work, we present a simple framework for 3D occupancy estimation, which is a CNN-based framework designed to reveal several key factors for 3D occupancy estimation, such as network design, optimization, and evaluation.

3D Object Detection 3D Reconstruction +4

Unsupervised Multimodal Change Detection Based on Structural Relationship Graph Representation Learning

1 code implementation3 Oct 2022 Hongruixuan Chen, Naoto Yokoya, Chen Wu, Bo Du

Subsequently, the similarity levels of two structural relationships are calculated from learned graph representations and two difference images are generated based on the similarity levels.

Change Detection Graph Representation Learning

EOD: The IEEE GRSS Earth Observation Database

no code implementations26 Sep 2022 Michael Schmitt, Pedram Ghamisi, Naoto Yokoya, Ronny Hänsch

In the era of deep learning, annotated datasets have become a crucial asset to the remote sensing community.

Earth Observation

Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

1 code implementation19 Jul 2022 Xiaoyu Dong, Naoto Yokoya, Longguang Wang, Tatsumi Uezato

Self-supervised cross-modal super-resolution (SR) can overcome the difficulty of acquiring paired training data, but is challenging because only low-resolution (LR) source and high-resolution (HR) guide images from different modalities are available.

Super-Resolution

V4d: voxel for 4d novel view synthesis

1 code implementation28 May 2022 Wanshui Gan, Hongbin Xu, Yi Huang, Shifeng Chen, Naoto Yokoya

The proposed LUTs-based refinement module achieves the performance gain with little computational cost and could serve as the plug-and-play module in the novel view synthesis task.

Novel View Synthesis

Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusion

1 code implementation7 May 2022 Danfeng Hong, Jing Yao, Deyu Meng, Naoto Yokoya, Jocelyn Chanussot

Enormous efforts have been recently made to super-resolve hyperspectral (HS) images with the aid of high spatial resolution multispectral (MS) images.

Hyperspectral Image Super-Resolution Image Super-Resolution +1

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework

1 code implementation CVPR 2022 Ningkai Mo, Wanshui Gan, Naoto Yokoya, Shifeng Chen

In this paper, a computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects.

3D Object Detection 6D Pose Estimation +1

Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixing

1 code implementation21 May 2021 Danfeng Hong, Lianru Gao, Jing Yao, Naoto Yokoya, Jocelyn Chanussot, Uta Heiden, Bing Zhang

Over the past decades, enormous efforts have been made to improve the performance of linear or nonlinear mixing models for hyperspectral unmixing, yet their ability to simultaneously generalize various spectral variabilities and extract physically meaningful endmembers still remains limited due to the poor ability in data fitting and reconstruction and the sensitivity to various spectral variabilities.

Hyperspectral Unmixing

Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing

no code implementations2 Mar 2021 Danfeng Hong, wei he, Naoto Yokoya, Jing Yao, Lianru Gao, Liangpei Zhang, Jocelyn Chanussot, Xiao Xiang Zhu

Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS).

Fast Hyperspectral Image Recovery via Non-iterative Fusion of Dual-Camera Compressive Hyperspectral Imaging

no code implementations30 Dec 2020 wei he, Naoto Yokoya, Xin Yuan

Specifically, the RGB measurement is utilized to estimate the coefficients, meanwhile the CASSI measurement is adopted to provide the orthogonal spectral basis.

Synthesizing Optical and SAR Imagery From Land Cover Maps and Auxiliary Raster Data

1 code implementation23 Nov 2020 Gerald Baier, Antonin Deschemps, Michael Schmitt, Naoto Yokoya

We synthesize both optical RGB and synthetic aperture radar (SAR) remote sensing images from land cover maps and auxiliary raster data using generative adversarial networks (GANs).

Decoder Image Generation

Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration

1 code implementation24 Oct 2020 wei he, Quanming Yao, Chao Li, Naoto Yokoya, Qibin Zhao, Hongyan zhang, Liangpei Zhang

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting.

Denoising Image Restoration

Joint and Progressive Subspace Analysis (JPSA) with Spatial-Spectral Manifold Alignment for Semi-Supervised Hyperspectral Dimensionality Reduction

1 code implementation21 Sep 2020 Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Jian Xu, Xiao Xiang Zhu

Conventional nonlinear subspace learning techniques (e. g., manifold learning) usually introduce some drawbacks in explainability (explicit mapping) and cost-effectiveness (linearization), generalization capability (out-of-sample), and representability (spatial-spectral discrimination).

Dimensionality Reduction

More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification

1 code implementation12 Aug 2020 Danfeng Hong, Lianru Gao, Naoto Yokoya, Jing Yao, Jocelyn Chanussot, Qian Du, Bing Zhang

In particular, we also investigate a special case of multi-modality learning (MML) -- cross-modality learning (CML) that exists widely in RS image classification applications.

Classification General Classification +3

Guided Deep Decoder: Unsupervised Image Pair Fusion

1 code implementation ECCV 2020 Tatsumi Uezato, Danfeng Hong, Naoto Yokoya, wei he

The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image.

Decoder Pansharpening

Illumination invariant hyperspectral image unmixing based on a digital surface model

no code implementations23 Jul 2020 Tatsumi Uezato, Naoto Yokoya, wei he

Although many spectral unmixing models have been developed to address spectral variability caused by variable incident illuminations, the mechanism of the spectral variability is still unclear.

Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping

1 code implementation9 Jun 2020 Naoto Yokoya, Kazuki Yamanoi, wei he, Gerald Baier, Bruno Adriano, Hiroyuki Miura, Satoru Oishi

We propose a framework that estimates inundation depth (maximum water level) and debris-flow-induced topographic deformation from remote sensing imagery by integrating deep learning and numerical simulation.

Change Detection

Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration

no code implementations6 Mar 2020 Jian Kang, Danfeng Hong, Jialin Liu, Gerald Baier, Naoto Yokoya, Begüm Demir

Interferometric phase restoration has been investigated for decades and most of the state-of-the-art methods have achieved promising performances for InSAR phase restoration.

Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization

no code implementations6 Jan 2020 Wei He, Yong Chen, Naoto Yokoya, Chao Li, Qibin Zhao

In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR.

Super-Resolution

Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification

no code implementations18 Dec 2019 Danfeng Hong, Xin Wu, Pedram Ghamisi, Jocelyn Chanussot, Naoto Yokoya, Xiao Xiang Zhu

In this paper, we propose a solution to address this issue by locally extracting invariant features from hyperspectral imagery (HSI) in both spatial and frequency domains, using a method called invariant attribute profiles (IAPs).

Attribute General Classification +2

Learning Shared Cross-modality Representation Using Multispectral-LiDAR and Hyperspectral Data

no code implementations18 Dec 2019 Danfeng Hong, Jocelyn Chanussot, Naoto Yokoya, Jian Kang, Xiao Xiang Zhu

Due to the ever-growing diversity of the data source, multi-modality feature learning has attracted more and more attention.

Diversity

Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net

1 code implementation27 Apr 2019 Ying Qu, Hairong Qi, Chiman Kwan, Naoto Yokoya, Jocelyn Chanussot

With this design, the network allows to extract correlated spectral and spatial information from unregistered images that better preserves the spectral information.

Hyperspectral Image Super-Resolution Image Super-Resolution

Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classification

no code implementations9 Jan 2019 Danfeng Hong, Naoto Yokoya, Nan Ge, Jocelyn Chanussot, Xiao Xiang Zhu

In this paper, we aim at tackling a general but interesting cross-modality feature learning question in remote sensing community --- can a limited amount of highly-discrimin-ative (e. g., hyperspectral) training data improve the performance of a classification task using a large amount of poorly-discriminative (e. g., multispectral) data?

General Classification

CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences

no code implementations30 Dec 2018 Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu

To achieve accurate land cover classification over a large coverage, we propose a cross-modality feature learning framework, called common subspace learning (CoSpace), by jointly considering subspace learning and supervised classification.

Classification General Classification +1

Multisource and Multitemporal Data Fusion in Remote Sensing

no code implementations19 Dec 2018 Pedram Ghamisi, Behnood Rasti, Naoto Yokoya, Qunming Wang, Bernhard Hofle, Lorenzo Bruzzone, Francesca Bovolo, Mingmin Chi, Katharina Anders, Richard Gloaguen, Peter M. Atkinson, Jon Atli Benediktsson

The sharp and recent increase in the availability of data captured by different sensors combined with their considerably heterogeneous natures poses a serious challenge for the effective and efficient processing of remotely sensed data.

An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing

no code implementations29 Oct 2018 Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu

To this end, we propose a novel spectral mixture model, called the augmented linear mixing model (ALMM), to address spectral variability by applying a data-driven learning strategy in inverse problems of hyperspectral unmixing.

Dictionary Learning Hyperspectral Unmixing

Joint & Progressive Learning from High-Dimensional Data for Multi-Label Classification

no code implementations ECCV 2018 Danfeng Hong, Naoto Yokoya, Jian Xu, Xiaoxiang Zhu

Despite the fact that nonlinear subspace learning techniques (e. g. manifold learning) have successfully applied to data representation, there is still room for improvement in explainability (explicit mapping), generalization (out-of-samples), and cost-effectiveness (linearization).

General Classification Multi-Label Classification +2

Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation

no code implementations26 Jul 2018 Wei He, Naoto Yokoya

In this paper, we present the optical image simulation from a synthetic aperture radar (SAR) data using deep learning based methods.

Cloud Removal Generative Adversarial Network

Hyperspectral pansharpening: a review

no code implementations17 Apr 2015 Laetitia Loncan, Luis B. Almeida, José M. Bioucas-Dias, Xavier Briottet, Jocelyn Chanussot, Nicolas Dobigeon, Sophie Fabre, Wenzhi Liao, Giorgio A. Licciardi, Miguel Simões, Jean-Yves Tourneret, Miguel A. Veganzones, Gemine Vivone, Qi Wei, Naoto Yokoya

In this work, we compare new pansharpening techniques designed for hyperspectral data with some of the state of the art methods for multispectral pansharpening, which have been adapted for hyperspectral data.

Pansharpening

Cannot find the paper you are looking for? You can Submit a new open access paper.