Multimodal Vision Research Laboratory

MVRL

Research Area: Image Localization

The goal of image localization is to estimate the geographic location (or scene-relative location) of an image (or video). We have worked on this problem for over 15 years, from a variety of perspectives. Our early work focused on localizing static outdoor cameras using temporal variations as a cue. More recent work has focused on the use of deep neural networks for single image localization, with a significant focus on exploiting overhead imagery for ground-level image localization. Current research includes unconstrained cross-view pose estimation, goal modality agnostic active geo-localization (GOMAA-Geo), and localizing limited field-of-view images using cross-view matching (ArcGeo). We also develop structure-aware methods for direct pose estimation and extend absolute pose regression to multiple scenes.

Publications

  1. Wollam A, Ashley K, Shugaev M, Arend O, Semenov IY, Dashtestani H, Ravi S, Jacobs N. 2026. Towards Unconstrained Cross-View Pose Estimation. In: IEEE Winter Conference on Applications of Computer Vision (WACV).
  2. Thumbnail for GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
    Sarkar A, Sastry S, Pirinen A, Zhang C, Jacobs N, Vorobeychik Y. 2024. GOMAA-Geo: GOal Modality Agnostic Active Geo-localization. In: Neural Information Processing Systems (NeurIPS).
  3. Shugaev M, Semenov I, Ashley K, Klaczynski M, Cuntoor N, Lee MW, Jacobs N. 2024. ArcGeo: Localizing Limited Field-of-View Images using Cross-view Matching. In: IEEE Winter Conference on Applications of Computer Vision (WACV).
  4. Xiong Z, Qiao F, Zhang Y, Jacobs N. 2023. StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation. In: British Machine Vision Conference (BMVC).
  5. Thumbnail for Content-Based Detection of Temporal Metadata Manipulation
    Padilha R, Salem T, Workman S, Andaló FA, Rocha A, Jacobs N. 2022. Content-Based Detection of Temporal Metadata Manipulation. IEEE Transactions on Information Forensics and Security:1316–1327. DOI: 10.1109/TIFS.2022.3159154.
  6. Thumbnail for A Structure-Aware Method for Direct Pose Estimation
    Blanton H, Workman S, Jacobs N. 2022. A Structure-Aware Method for Direct Pose Estimation. In: IEEE Winter Conference on Applications of Computer Vision (WACV). DOI: 10.1109/WACV51458.2022.00028.
  7. Blanton H, Greenwell C, Workman S, Jacobs N. 2020. Extending Absolute Pose Regression to Multiple Scenes. In: Joint Workshop on Long-Term Visual Localization, Visual Odometry and Geometric and Learning-based SLAM (CVPR Workshop). DOI: 10.1109/CVPRW50498.2020.00027.
  8. Thumbnail for Learning a Dynamic Map of Visual Appearance
    Salem T, Workman S, Jacobs N. 2020. Learning a Dynamic Map of Visual Appearance. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI: 10.1109/CVPR42600.2020.01245.
  9. Thumbnail for Learning Geo-Temporal Image Features
    Zhai M, Salem T, Greenwell C, Workman S, Pless R, Jacobs N. 2018. Learning Geo-Temporal Image Features. In: British Machine Vision Conference (BMVC).
  10. Thumbnail for Predicting Ground-Level Scene Layout from Aerial Imagery
    Zhai M, Bessinger Z, Workman S, Jacobs N. 2017. Predicting Ground-Level Scene Layout from Aerial Imagery. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI: 10.1109/CVPR.2017.440.
  11. Vo N, Jacobs N, Hays J. 2017. Revisiting IM2GPS in the Deep Learning Era. In: IEEE International Conference on Computer Vision (ICCV). DOI: 10.1109/ICCV.2017.286.
  12. Thumbnail for Horizon Lines in the Wild
    Workman S, Zhai M, Jacobs N. 2016. Horizon Lines in the Wild. In: British Machine Vision Conference (BMVC).
  13. Zhai M, Workman S, Jacobs N. 2016. Camera Geo-Calibration using an MCMC Approach. In: IEEE International Conference on Image Processing (ICIP). DOI: 10.1109/ICIP.2016.7532905.
  14. Baltenberger R, Zhai M, Greenwell C, Workman S, Jacobs N. 2016. A Fast Method for Estimating Transient Scene Properties. In: IEEE Winter Conference on Applications of Computer Vision (WACV). 1–8. DOI: 10.1109/WACV.2016.7477713.
  15. Islam MT, Workman S, Jacobs N. 2015. Face2GPS: Estimating Geographic Location from Facial Features. In: IEEE International Conference on Image Processing (ICIP). DOI: 10.1109/ICIP.2015.7351072.
  16. Thumbnail for Wide-Area Image Geolocalization with Aerial Reference Imagery
    Workman S, Souvenir R, Jacobs N. 2015. Wide-Area Image Geolocalization with Aerial Reference Imagery. In: IEEE International Conference on Computer Vision (ICCV). 1–9. DOI: 10.1109/ICCV.2015.451.
  17. Workman S, Jacobs N. 2015. On the Location Dependence of Convolutional Neural Network Features. In: IEEE/ISPRS Workshop: Large Scale Computer Vision for Remote Sensing (EARTHVISION). 1–9. DOI: 10.1109/CVPRW.2015.7301385.
  18. Jacobs N, Miskell K, Pless R. 2011. Webcam Geo-localization using Aggregate Light Levels. In: IEEE Workshop on Applications of Computer Vision (WACV). 132–138. DOI: 10.1109/WACV.2011.5711494.
  19. Jacobs N, Roman N, Pless R. 2008. Toward Fully Automatic Geo-Location and Geo-Orientation of Static Outdoor Cameras. In: IEEE Workshop on Applications of Computer Vision (WACV). 1–6. DOI: 10.1109/WACV.2008.4544040.
  20. Thumbnail for Geolocating Static Cameras
    Jacobs N, Satkin S, Roman N, Speyer R, Pless R. 2007. Geolocating Static Cameras. In: IEEE International Conference on Computer Vision (ICCV). 1–6. DOI: 10.1109/ICCV.2007.4408995.