Skip to content

@VisionXLab VisionXLab

Change the repository type filter

All

    Repositories list

    36 repositories

    • CitationClaw

      Public
      让每一次引用都成为可解释的影响力 Turning Every Citation into Explainable Impact
      Python
      •
      Other
      •6•180•2•2•Updated Mar 18, 2026Mar 18, 2026

    • Awesome-RS-VL-Data

      Public
      Awesome Remote Sensing Vision-Language Datasets
      MIT License
      •2•61•128•0•Updated Mar 17, 2026Mar 17, 2026

    • point2rbox-v2

      Public
      [CVPR'25] Official repo of "Point2RBox-v2：Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances"
      Python
      •4•40•0•0•Updated Mar 16, 2026Mar 16, 2026

    • AdapTok

      Public
      [CVPR'26] AdapTok: Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space
      Python
      •
      MIT License
      •1•23•2•0•Updated Mar 15, 2026Mar 15, 2026

    • GRADE

      Public
      GRADE: Grounded Reasoning Assessment for Discipline-informed Editing
      Python
      •0•23•0•0•Updated Mar 15, 2026Mar 15, 2026

    • CastDet

      Public
      [ECCV'24/IJCV'26] Code repo for "Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning"
      Python
      •
      Apache License 2.0
      •4•76•5•0•Updated Mar 15, 2026Mar 15, 2026

    • EvoTok

      Public
      Code repo for "EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation"
      0•14•0•0•Updated Mar 15, 2026Mar 15, 2026

    • FIRM-Reward

      Public
      Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
      Python
      •
      Other
      •0•30•1•0•Updated Mar 13, 2026Mar 13, 2026

    • CrossEarth-SAR

      Public
      The official repo of CrossEarth-SAR, a sar-centric and billion-scale geospatial foundation model for cross-domain semantic segmentation
      Python
      •0•28•1•0•Updated Mar 12, 2026Mar 12, 2026

    • Rise-Video

      Public
      RISE-Video: Can Video Generators Decode Implicit World Rules?
      Python
      •0•22•2•0•Updated Mar 11, 2026Mar 11, 2026

    • PWOOD

      Public
      [CVPR'26] Partial Weakly-Supervised Oriented Object Detection
      Python
      •0•8•0•0•Updated Mar 4, 2026Mar 4, 2026

    • Point2RBox-v3

      Public
      [ICLR'26] Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
      Python
      •1•12•0•0•Updated Feb 28, 2026Feb 28, 2026

    • LRS-VQA

      Public
      [ICCV'25] When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
      Python
      •1•48•2•0•Updated Feb 16, 2026Feb 16, 2026

    • SPWOOD

      Public
      [ICLR'26] SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection
      Jupyter Notebook
      •0•1•1•0•Updated Feb 15, 2026Feb 15, 2026

    • RSCoVLM

      Public
      [Remote Sensing 2026] Co-Training Vision Language Models for Remote Sensing Multi-task Learning
      Jupyter Notebook
      •0•26•0•0•Updated Feb 12, 2026Feb 12, 2026

    • mllm-mmrotate

      Public
      [IGARSS 2025 Oral] A Simple Aerial Detection Baseline of Multimodal Language Models.
      Jupyter Notebook
      •6•92•0•1•Updated Feb 12, 2026Feb 12, 2026

    • OF-Diff

      Public
      [ICLR'26] OF-Diff: Object Fidelity Diffusion for Remote Sensing Image Generation
      Python
      •0•28•3•0•Updated Feb 6, 2026Feb 6, 2026

    • VisionXLab_LaTeX_Template

      Public
      TeX
      •0•7•0•0•Updated Feb 3, 2026Feb 3, 2026

    • SpaCE-10

      Public
      [ICLR 2026] SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
      Python
      •2•18•1•0•Updated Jan 26, 2026Jan 26, 2026

    • DVGBench

      Public
      [ISPRS2026] DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models
      0•21•3•0•Updated Jan 14, 2026Jan 14, 2026

    • AirSpatialBot

      Public
      [TGRS'25] AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval
      Python
      •1•29•1•0•Updated Jan 6, 2026Jan 6, 2026

    • avi-math

      Public
      [ISPRS'25] Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration
      Python
      •1•14•0•0•Updated Jan 4, 2026Jan 4, 2026

    • CrossEarth

      Public
      [TPAMI 2025] CrossEarth: Geospatial Vision Foundation Model for Cross-Domain Generalization in Remote Sensing Semantic Segmentation
      Python
      •
      MIT License
      •9•180•3•0•Updated Dec 21, 2025Dec 21, 2025

    • ProCLIP

      Public
      Official PyTorch implementation of ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
      Python
      •2•23•1•0•Updated Dec 4, 2025Dec 4, 2025

    • PointOBB-v3

      Public
      [IJCV] PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection
      Python
      •
      MIT License
      •2•40•1•0•Updated Sep 25, 2025Sep 25, 2025

    • Earth-Adapter

      Public
      [AAAI 26] Official PyTorch implementation of Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation
      Python
      •
      GNU General Public License v3.0
      •1•57•1•0•Updated May 29, 2025May 29, 2025

    • GeoGround

      Public
      GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
      2•80•5•0•Updated May 10, 2025May 10, 2025

    • PointOBB-v2

      Public
      [ICLR'25] Official repo of "PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection"
      Python
      •
      Apache License 2.0
      •5•38•5•0•Updated Mar 27, 2025Mar 27, 2025

    • whollywood-jittor

      Public
      [TPAMI] Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Feb 14, 2025Feb 14, 2025

    • whollywood

      Public
      [TPAMI] Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection
      Jupyter Notebook
      •
      Apache License 2.0
      •0•11•1•0•Updated Feb 14, 2025Feb 14, 2025