v0.4.0

Major update to support Lightning 2 (finally!). However, it also introduces breaking changes from the previous v0.3 code. See the details below.

• Transitioning from v0.3 to v0.4: check the v0.4 upgrade guide
• Added features:
  • Support for YAML config files. See the config file documentation
  • Table comparing PTLFlow results with the original papers to check the stability of the included models.
• Added new models:
  • NeuFlow v2 https://arxiv.org/abs/2408.10161
• Add support for more datasets:
  • Middlebury-ST [https://vision.middlebury.edu/stereo/data/scenes2014/]{https://vision.middlebury.edu/stereo/data/scenes2014/}
  • VIPER https://playing-for-benchmarks.org/

v0.3.2

Added

• New models:
  • MemFlow
  • NeuFlow
  • SEA-RAFT
  • SplatFlow
• New datasets
  • Kubric
  • TartanAir
• ONNX and TensorRT conversion scripts to RAPIDFlow

Fixed

• LR scheduler when accumulating gradients

v0.3.1

Added

• New models:
  • CCMR
  • LLA-Flow
  • RAPIDFlow
• FP16 inference in most models
• Script to plot results

v0.3.0

This is a major update and introduces breaking changes to v0.2.
The list of changes below is not comprehensive, there may be other changes that are not listed.

Added

• New models:
  • DIP
  • Flow1D
  • FlowFormer++
  • GMFlow+
  • MatchFlow
  • MS-RAFT+
  • RPKNet
    -SeparableFlow
  • SKFlow
  • VideoFlow
• New datasets:
  • Middlebury
  • Monkaa
  • Spring
• Option to use RAFT's alt_cuda_corr for supported models
  • Also added a pure PyTorch version of alt_cuda_corr, which is slower but does not need to be compiled

Fixed

• Compatibility with PyTorch 2.0, 2.1
• Compatibility issues with PyTorch Lightning 1.9
• Resizing augmentation when the valid mask is sparse
• Models should produce results more similar to the paper
  • HOWEVER, we do not guarantee our results are correct. Use the official implementations for the most accurate results.

Changed

• Each model now handle its own IO reshaping, instead of using padding for all models
• speed_benchmark.py becomes model_benchmark.py and records more metrics
• Renamed model: pwcdcnet -> pwcnet, pwcnet -> pwcnet_nodc
• Updated requirements, support for many old versions are dropped
  • Important requirements:
    • python>=3.8,<3.12
    • torch>=1.13,<2.2
    • lightning>=1.9.0,<2

v0.2.7

Fixed

• Memory leak in FlowMetrics caused when setting full_state_update=False

v0.2.6

Added

• Support for AutoFlow dataset
• New models:
  • CRAFT
  • CSFlow
  • FlowFormer
  • GMFlow
  • GMFlowNet

Fixed

• Compatibility issues with PyTorch Lightning 1.6

v0.2.5

Added

• FastFlowNet model

Fixed

• Check if max_steps has negative value (the new standard value in newer PyTorch Lightning versions)

0.2.4

Added

• GMA model
• SCV model

0.2.3

Added

• DICL model
• LCV with RAFT model

Fixed

• Check if an input is an array before showing as an image during validation

0.2.2

Added

• MaskFlownet model
• Script for generating predictions for the test split of some datasets (currently Sintel and KITTI)

Fixed

• Inference uses no_grad annotation
• Threshold values for computing outlier metric and update table of results
• Some utility functions did not pass through all the keys from the input dicts