Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios

@article{Gruber2019PixelAccurateDE,
  title={Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios},
  author={Tobias Gruber and Mario Bijelic and Felix Heide and Werner Ritter and K. Dietmayer},
  journal={2019 International Conference on 3D Vision (3DV)},
  year={2019},
  pages={95-105}
}
  • Tobias Gruber, Mario Bijelic, +2 authors K. Dietmayer
  • Published in
    International Conference on…
    2019
  • Computer Science
  • Highlight Information
    This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25" (arcsecond), akin to a 50 megapixel camera with per-pixel depth available. [...] Key Method We propose an evaluation methodology in four characteristic automotive scenarios recorded in varying weather conditions (day, night, fog, rain). As a result, our benchmark allows us to evaluate the robustness of depth sensing methods in adverse weather and…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    CNN-Based Lidar Point Cloud De-Noising in Adverse Weather

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 64 REFERENCES

    VirtualWorlds as Proxy for Multi-object Tracking Analysis

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Vision meets robotics: The KITTI dataset

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Pyramid Stereo Matching Network

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Sparsity Invariant CNNs

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Unsupervised Monocular Depth Estimation with Left-Right Consistency

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Stereo Processing by Semiglobal Matching and Mutual Information

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Depth Coefficients for Depth Completion

    VIEW 1 EXCERPT

    Learning the Depths of Moving People by Watching Frozen People

    VIEW 2 EXCERPTS

    SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation