rsdler/Remote-Sensing-in-CVPR2024

Papers related to remote sensing in CVPR 2024

Remote Sensing in CVPR2024

Papers related to remote sensing in CVPR2024

CVPR 2023

1. Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels [Highlight]

• Paper : http://arxiv.org/abs/2403.02746

• Code: https://github.com/LiZhuoHong/Paraformer

• Data: https://github.com/LiZhuoHong/Paraformer

2. SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation [Highlight]

• Paper : https://arxiv.org/abs/2404.02638v1
• Code: https://github.com/yejy53/SG-BEV

3. S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data [Oral]

• Paper: CVPR 2024 Paper
• Video: https://www.youtube.com/watch?v=VPyomVPVqwU

4. GeoChat : Grounded Large Vision-Language Model for Remote Sensing

• Paper : https://arxiv.org/abs/2311.15826

• Code: https://github.com/mbzuai-oryx/geochat

• Data: https://huggingface.co/datasets/MBZUAI/GeoChat_Instruct

5. SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery

• Paper : https://arxiv.org/abs/2312.10115

6. Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion

• Paper : https://arxiv.org/abs/2401.10786

7. Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation

• Paper : https://arxiv.org/abs/2312.12470
• Code: https://github.com/Lsan2401/RMSIN
• Data: https://github.com/Lsan2401/RMSIN

8. Poly Kernel Inception Network for Remote Sensing Detection

• Paper : http://arxiv.org/abs/2403.06258
• Code: https://github.com/NUST-Machine-Intelligence-Laboratory/PKINet

9. Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery

• Paper : http://arxiv.org/abs/2403.05419

• Code: https://github.com/techmn/satmae_pp

10. Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model

• Paper : https://arxiv.org/abs/2403.17460v1
• Code: https://github.com/dongrunmin/RefDiff

11. Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery

• Paper : https://arxiv.org/abs/2403.11812v1
• Code: https://github.com/zyqz97/Aerial_lifting

12. SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation

• Paper : https://arxiv.org/abs/2403.16605v1

13. Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization

• Paper : http://arxiv.org/abs/2403.14198
• Code: https://github.com/liguopeng0923/UCVGL

14. PointOBB: Learning Oriented Object Detection via Single Point Supervision

• Paper : https://arxiv.org/abs/2311.14757

• Code: https://github.com/Luo-Z13/pointobb

15. Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

• Paper : http://arxiv.org/abs/2311.14758

• Code: https://github.com/yuyi1005/point2rbox-mmrotate

16. Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening

• Paper : http://arxiv.org/abs/2404.07543

• Code: https://github.com/duanyll/CANConv

17. 3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions

• Paper : http://arxiv.org/abs/2404.04823

• Code: https://github.com/opendatalab/MLS-BRN

18. Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans

• Paper : http://arxiv.org/abs/2304.09704
• Code: https://romainloiseau.fr/learnable-earth-parser/
• Data: https://romainloiseau.fr/learnable-earth-parser/

19. Bridging Remote Sensors with Multisensor Geospatial Foundation Models

• Paper : http://arxiv.org/abs/2404.01260
• Code: https://github.com/boranhan/Geospatial_Foundation_Models

20. CityDreamer: Compositional Generative Model of Unbounded 3D Cities

• Paper : https://arxiv.org/abs/2311.15826
• Code: https://github.com/mbzuai-oryx/geochat
• Data: https://huggingface.co/datasets/MBZUAI/GeoChat_Instruct

21. WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification

• Paper : CVPR 2024 Paper
• Code: https://github.com/UCSB-VRL/WildlifeMapper

22. Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection

• Paper: CVPR 2024 Paper

23. Parameter Efficient Self-Supervised Geospatial Domain Adaptation

• Paper: CVPR 2024 Paper
• Code: https://github.com/HSG-AIML/GDA

24. Relational Matching for Weakly Semi-Supervised Oriented Object Detection

• Paper: CVPR 2024 Paper
• Code: https://github.com/HSG-AIML/GDA

25. Multi-modal Learning for Geospatial Vegetation Forecasting

• Paper: CVPR 2024 Paper
• Code: https://github.com/vitusbenson/greenearthnet

26. DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting

• Paper: CVPR 2024 Paper
• Code: https://github.com/DeminYu98/DiffCast

27. Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising

• Paper: CVPR 2024 Paper

CVPR 2024 Workshop: EarthVision: Large Scale Computer Vision for Remote Sensing Imagery

1. Efficient Local Correlation Volume for Unsupervised Optical Flow Estimation on Small Moving Objects in Large Satellite Images

• Page : CVPR24 workshop Paper

2. GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis

• Page : CVPR24 workshop Paper

3. Contrastive Pretraining for Visual Concept Explanations of Socioeconomic Outcomes

• Page : CVPR24 workshop Paper

4. Detecting Out-Of-Distribution Earth Observation Images with Diffusion Models

• Page : CVPR24 workshop Paper

5. Let Me Show You How It's Done - Cross-modal Knowledge Distillation as Pretext Task for Semantic Segmentation

• Page : CVPR24 workshop Paper

6. Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs

• Page : CVPR24 workshop Paper

7. SyntStereo2Real: Edge-Aware GAN for Remote Sensing Image-to-Image Translation while Maintaining Stereo Constraint

• Page : CVPR24 workshop Paper

8. Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Images

• Page : CVPR24 workshop Paper

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

• Page : CVPR24 workshop Paper

10. Implicit Assimilation of Sparse In Situ Data for Dense & Global Storm Surge Forecasting

• Page : CVPR24 workshop Paper

11. SUNDIAL: 3D Satellite Understanding through Direct Ambient and Complex Lighting Decomposition

• Page : CVPR24 workshop Paper

12. Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery

• Page : CVPR24 workshop Paper

13. Cross-sensor super-resolution of irregularly sampled Sentinel-2 time series

• Page : CVPR24 workshop Paper

14. (Street) Lights Will Guide You: Georeferencing Nighttime Astronaut Photography of Earth

• Page : CVPR24 workshop Paper

15. Radar Fields: An Extension of Radiance Fields to SAR

• Page : CVPR24 workshop Paper

16. Deep Generative Data Assimilation in Multimodal Setting

• Page : CVPR24 workshop Paper

17. GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots

• Page : CVPR24 workshop Paper

18. UrbanSARFloods: Sentinel-1 SLC-Based Benchmark Dataset for Urban and Open-Area Flood Mapping

• Page : CVPR24 workshop Paper

CVPR 2024 Papers in other workshops

1. Segment Anything Model for Road Network Graph Extraction

• Workshop: CVPR 2024 2nd Workshop on Scene Graphs and Graph Representation Learning
• Paper : http://arxiv.org/abs/2403.16051
• Code: https://github.com/htcr/sam_road

2. Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Framework

• Workshop: CVPR 2024 3rd Workshop on Learning with Limited Labelled Data for Image and Video Understanding
• Paper: http://arxiv.org/abs/2404.12721
• Code: https://github.com/LiZhuoHong/SegLand
• Page: https://cliffbb.github.io/OEM-Fewshot-Challenge/

3. Class Similarity Transition: Decoupling Class Similarities and Imbalance from Generalized Few-shot Segmentation

• Workshop: CVPR 2024 3rd Workshop on Learning with Limited Labelled Data for Image and Video Understanding
• Paper : http://arxiv.org/abs/2404.05111
• Code: https://github.com/earth-insights/ClassTrans
• Page: https://cliffbb.github.io/OEM-Fewshot-Challenge/

4. Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing Domain

• Workshop: CVPR 2024 3rd Workshop on Learning with Limited Labelled Data for Image and Video Understanding
• Paper : https://arxiv.org/abs/2404.10307
• Page : https://codalab.lisn.upsaclay.fr/competitions/17568