Gated2Depth: Real-Time Dense Lidar From Gated Images

@article{Gruber2019Gated2DepthRD,
  title={Gated2Depth: Real-Time Dense Lidar From Gated Images},
  author={Tobias Gruber and Frank D. Julca-Aguilar and Mario Bijelic and W. Ritter and K. Dietmayer and Felix Heide},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={1506-1516}
}
  • Tobias Gruber, Frank D. Julca-Aguilar, +3 authors Felix Heide
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • We present an imaging framework which converts three images from a gated camera into high-resolution depth maps with depth resolution comparable to pulsed lidar measurements. [...] Key Method The proposed architecture exploits semantic context across gated slices, and is trained on a synthetic discriminator loss without the need of dense depth labels. The method is real-time and essentially turns a gated camera into a low-cost dense flash lidar which we validate on a wide range of outdoor driving captures and…Expand Abstract
    13 Citations
    Uncertainty depth estimation with gated images for 3D reconstruction
    • 2
    • PDF
    Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios
    • 4
    • PDF
    STORM: Super-resolving Transients by OveRsampled Measurements
    Ellipsoidal path connections for time-gated rendering
    • 3
    • PDF
    Polka Lines: Learning Structured Illumination and Reconstruction for Active Stereo
    • PDF
    ISETAuto: Detecting vehicles with depth and radiance information
    • PDF
    Towards a MEMS-based Adaptive LIDAR
    • PDF

    References

    SHOWING 1-10 OF 80 REFERENCES
    Three-dimensional range-gated imaging at infrared wavelengths with super-resolution depth mapping
    • 26
    Estimating Depth from RGB and Sparse Sensing
    • 48
    • PDF
    Semi-Supervised Deep Learning for Monocular Depth Map Prediction
    • 367
    • PDF
    Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
    • Fangchang Ma, S. Karaman
    • Computer Science, Engineering
    • 2018 IEEE International Conference on Robotics and Automation (ICRA)
    • 2018
    • 221
    • Highly Influential
    • PDF
    Self-Supervised Sparse-to-Dense: Self-Supervised Depth Completion from LiDAR and Monocular Camera
    • 120
    • Highly Influential
    • PDF
    Deep End-to-End Time-of-Flight Imaging
    • 31
    • PDF
    Learning Depth from Single Monocular Images
    • 841
    • PDF
    Long-range three-dimensional active imaging with superresolution depth mapping.
    • 114
    Geometry meets semantics for semi-supervised monocular depth estimation
    • 46
    • PDF
    Deeper Depth Prediction with Fully Convolutional Residual Networks
    • 886
    • PDF