Corpus ID: 227745070

Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos

  title={Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos},
  author={K. Maninis and S. Popov and M. Nie{\ss}ner and V. Ferrari},
  • K. Maninis, S. Popov, +1 author V. Ferrari
  • Published 2020
  • Computer Science
  • ArXiv
  • We address the task of aligning CAD models to a video sequence of a complex scene containing multiple objects. Our method is able to process arbitrary videos and fully automatically recover the 9 DoF pose for each object appearing in it, thus aligning them in a common 3D coordinate frame. The core idea of our method is to integrate neural network predictions from individual frames with a temporally global, multi-view constraint optimization formulation. This integration process resolves the… CONTINUE READING

    Figures and Tables from this paper


    End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans
    • 19
    • PDF
    3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare
    • 129
    • PDF
    FroDO: From Detections to 3D Objects
    • 6
    • PDF
    CoReNet: Coherent 3D scene reconstruction from a single RGB image
    • 3
    • PDF
    Scene Recomposition by Learning-Based ICP
    • Hamid Izadinia, S. Seitz
    • Computer Science
    • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2020
    • 2
    • PDF
    Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
    • 54
    • PDF
    Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
    • 3
    • Highly Influential
    • PDF
    3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
    • 741
    • PDF
    Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image
    • 12
    • PDF