TGM v0.1.0 Roadmap

[edgarriba]

This is the roadmap for torchgeometry v0.1.0 focuses on multi-view reprojection primitives that work on images and feature maps.

• Feel free to volunteer yourself if you are interested in trying out some items(they do not have to be on the list).

Features

• API
  • Pinhole
    • inverse_pose 001097c
    • pinhole_matrix 063b0c6
    • inverse_pinhole_matrix 063b0c6
    • scale_pinhole 063b0c6
    • homography_i_H_ref 063b0c6
  • Conversions
    • pi fb56c9c
    • rad2deg fb56c9c
    • deg2rad fb56c9c
    • convert_points_from_homogeneous f13c462
    • convert_points_to_homogeneous f13c462
    • transform_points 1a1511c
    • angle_axis_to_rotation_matrix 4c929d5
    • rtvec_to_pose 4c929d5
    • rotation_matrix_to_angle_axis f999165
    • rotation_matrix_to_quaternion f999165
    • quaternion_to_angle_axis f999165
  • Warping
    • HomographyWarper 2e54229
    • DepthWarper cd03569
  • Utilities
    • tensor_to_image 3ad7d05
    • image_to_tensor 3ad7d05
    • inverse 1a1511c
• Testing
  • docker kit ae8d9e1
  • automated test with TravisCI c213e3e
  • lint tests c213e3e
  • cuda tests (v0.1.1)
• Documentation
  • sphinx documentation b9251ab
  • development e800c36
• Examples:
  • homography regression ce1524d
  • image warped by depth f999165
  • jupiter notebooks 3c96835

[edgarriba]

we should consider importing stuff from GVNN: https://github.com/ankurhanda/gvnn

[ankurhanda]

I will be more than happy to add new functionality to it --- robot kinematics and other stuff that I have already implemented but in tensorflow :) so we could import both gvnn and that as well.