Skip to content

@edgarriba edgarriba released this Mar 14, 2019 · 264 commits to master since this release


  • Migrated the project to Arraiy Open Source Organization: 48ad11f
  • Update with support of PyTorch v1.0.1. In fact, we test each time against nightly builds. 5c9d9ae
  • Fix issue with pip package PyTorch minimal version. Now we require at least v1.0.0. 6e16734
  • Package version file is auto-generate and too keep tracked sha. f337b3c
  • Added codecov support to keep tracked tested code. e609b21

Breaking Changes

  • Refactor DepthWarper API - now accepts PinholeCamera objects as parameters:
>>> # pinholes camera models
>>> pinhole_dst = tgm.PinholeCamera(...)
>>> pinhole_src = tgm.PinholeCamera(...)
>>> # create the depth warper, compute the projection matrix
>>> warper = tgm.DepthWarper(pinhole_dst, height, width)
>>> warper.compute_projection_matrix(pinhole_src)
>>> # warp the destionation frame to reference by depth
>>> depth_src = torch.ones(1, 1, 32, 32)  # Nx1xHxW
>>> image_dst = torch.rand(1, 3, 32, 32)  # NxCxHxW
>>> image_src = warper(depth_src, image_dst)  # NxCxHxW

New Features

  • Added new PinholeCamera API to represent pinhole camera models. b6ec592
  • Refactor and moved code from and created a dedicated module for linear transforms a1c25b1
    • boxplus_transformation, boxminus_transformation, inverse_transformation, transform_points.
  • Added a collection of losses:
  • Added SpatialSoftArgmax2d operator to extract 2D coordinates from probability maps. cf7bb29
  • Added extract_tensor_patches routine similar to tf.extract_image_patches but for multidimensional tensors instead of images. f60fa57
  • Added boxplus_transform and boxminus_transform to compose or compute relative pose functions. e0882ea

Bug Fixes

  • Fixed DepthWarper in order to accept mini-batch computation. 7175b4f
  • Added missing tests for warp_affine. 57cbd29
  • Fixed and refactored quaternion_to_axis_angle and axis_angle_to_quaternion to avoid nans. 4aa0bca



Assets 2

Table of Contents

  • Breaking Changes
  • New Features
  • Bug Fixes
  • Documentation improvements

Breaking Changes

  • tgm.inverse has been removed since now Pytorch supports batched version for torch.inverse f6c210d

New Features

  • Added tgm.warp_perspective matching OpenCV interface d53cbce
  • Added tgm.get_perspective_transform matching OpenCV interface
  • Added tgm.get_rotation_matrix2d matching OpenCV interface

Bug Fixes

  • Fixed bug for inplace operation in tgm.inverse_pose 0aba15d

Documentation improvements

  • Added notebook tutorial for tgm.warp_affine and tgm.warp_pesrpective 894bf52

Other improvements

  • Update to Pytorch v1.0.0 3ee14c8
  • Refactor in testing framework. Removed unittest and now using pytest since it's easy to parametrize unit tests.
    • parametrized tests for different batch sizes
    • parametrized tests for device types: cpu and cuda. Note: need to test on cuda yet.
  • Now we have official pip package to install the library: pip install torchgeometry
Assets 2

@edgarriba edgarriba released this Oct 3, 2018 · 582 commits to master since this release

This is the initial release of the torchvision package.

It contains a set of routines and modules for geometric computer vision implementing multi-view reprojection primitives that work on images and feature maps warping. In addition, we provide routines for conversions and utilities for the pinhole model cameras.

Table of Contents





Assets 2
You can’t perform that action at this time.