======================== List of available models ======================== Below is a list and a brief explanation about the models currently available on PTLFlow. List of models ============== CCMR ---- `[source code] `__ - Paper: **CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning** - `https://arxiv.org/abs/2311.02661 `_ - Reference code: `https://github.com/cv-stuttgart/CCMR `_ - Model names: ``ccmr``, ``ccmr_p`` CRAFT ----- `[source code] `__ - Paper: **CRAFT: Cross-Attentional Flow Transformers for Robust Optical Flow** - `https://arxiv.org/abs/2203.16896 `_ - Reference code: `https://github.com/askerlee/craft `_ - Model names: ``craft`` CSFlow ------ `[source code] `__ - Paper: **CSFlow: Learning optical flow via cross strip correlation for autonomous driving** - `https://arxiv.org/abs/2202.00909 `_ - Reference code: `https://github.com/MasterHow/CSFlow `_ - Model names: ``csflow`` DICL-Flow --------- `[source code] `__ - Paper: **Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation** - `https://arxiv.org/abs/2010.14851 `_ - Reference code: `https://github.com/jytime/DICL-Flow `_ - Model names: ``dicl`` DIP --- `[source code] `__ - Paper: **DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow** - `https://arxiv.org/abs/2204.00330 `_ - Reference code: `https://github.com/zihuazheng/DIP `_ - Model names: ``dip`` FastFlownet ----------- `[source code] `__ - Paper: **FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation** - `https://arxiv.org/abs/2103.04524 `_ - Reference code: `https://github.com/ltkong218/FastFlowNet `_ - Model names: ``fastflownet`` Flow1D ------ `[source code] `__ - Paper: **High-Resolution Optical Flow from 1D Attention and Correlation** - `https://arxiv.org/abs/2104.13918 `_ - Reference code: `https://github.com/haofeixu/flow1d `_ - Model names: ``flow1d`` FlowFormer ---------- `[source code] `__ - Paper: **FlowFormer: A Transformer Architecture for Optical Flow** - `https://arxiv.org/abs/2203.16194 `_ - Reference code: `https://github.com/drinkingcoder/FlowFormer-Official `_ - Model names: ``flowformer`` FlowFormer++ ------------ `[source code] `__ - Paper: **Flowformer++: Masked cost volume autoencoding for pretraining optical flow estimation** - `https://arxiv.org/abs/2303.01237 `_ - Reference code: `https://github.com/XiaoyuShi97/FlowFormerPlusPlus `_ - Model names: ``flowformer_pp`` Flownet ------- `[source code] `__ - Papers: - **FlowNet: Learning Optical Flow with Convolutional Networks** - `https://arxiv.org/abs/1504.06852 `_ - **FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks** - `https://arxiv.org/abs/1612.01925 `_ - Reference code: `https://github.com/NVIDIA/flownet2-pytorch `_ - Model names: ``flownets``, ``flownetc``, ``flownet2``, ``flownetcs``, ``flownetcss``, ``flownetsd`` GMA --- `[source code] `__ - Paper: **Learning to Estimate Hidden Motions with Global Motion Aggregation** - `https://arxiv.org/abs/2104.02409 `_ - Reference code: `https://github.com/zacjiang/GMA `_ - Model names: ``gma`` GMFlow ------ `[source code] `__ - Paper: **GMFlow: Learning Optical Flow via Global Matching** - `https://arxiv.org/abs/2111.13680 `_ - Reference code: `https://github.com/haofeixu/gmflow `_ - Model names: ``gmflow``, ``gmflow_refine`` GMFlow+, UniMatch ----------------- `[source code] `__ - Paper: **Unifying Flow, Stereo and Depth Estimation** - `https://arxiv.org/abs/2211.05783 `_ - Reference code: `https://github.com/autonomousvision/unimatch `_ - Model names: ``gmflow_p``, ``gmflow_p_sc2``, ``gmflow_p_sc2_ref6``, ``unimatch``, ``unimatch_sc2``, ``unimatch_sc2_ref6`` GMFlowNet --------- `[source code] `__ - Paper: **Global Matching with Overlapping Attention for Optical Flow Estimation** - `https://arxiv.org/abs/2203.11335 `_ - Reference code: `https://github.com/xiaofeng94/GMFlowNet `_ - Model names: ``gmflownet``, ``gmflownet_mix`` HD3 --- `[source code] `__ - Paper: **Hierarchical Discrete Distribution Decomposition for Match Density Estimation** - `https://arxiv.org/abs/1812.06264 `_ - Reference code: `https://github.com/ucbdrive/hd3 `_ - Model names: ``hd3``, ``hd3_ctxt`` IRR --- `[source code] `__ - Paper: **Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation** - `https://arxiv.org/abs/1904.05290 `_ - Reference code: `https://github.com/visinf/irr `_ - Model names: ``irr_pwc``, ``irr_pwcnet``, ``irr_pwcnet_irr`` LCV --- `[source code] `__ - Paper: **Learnable Cost Volume Using the Cayley Representation** - `https://arxiv.org/abs/2007.11431 `_ - Reference code: `https://github.com/Prinsphield/LCV `_ - Model names: ``lcv_raft``, ``lcv_raft_small`` LiteFlowNet ----------- `[source code] `__ - Paper: **LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation** - `https://arxiv.org/abs/1805.07036 `_ - Reference code: `https://github.com/twhui/LiteFlowNet `__ - Model name: ``liteflownet`` LiteFlowNet2 ------------ `[source code] `__ - Paper: **A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization** - `https://ieeexplore.ieee.org/document/9018073 `_ - Reference code: `https://github.com/twhui/LiteFlowNet2 `__ - Model names: ``liteflownet2``, ``liteflownet2_pseudoreg`` LiteFlowNet3 ------------ `[source code] `__ - Paper: **LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation** - `https://arxiv.org/abs/2007.09319 `_ - Reference code: `https://github.com/twhui/LiteFlowNet3 `__ - Model names: ``liteflownet3``, ``liteflownet3_pseudoreg``, ``liteflownet3s``, ``liteflownet3s_pseudoreg`` LLA-Flow -------- `[source code] `__ - Paper: **LLA-Flow: A Lightweight Local Aggregation on Cost Volume for Optical Flow Estimation** - `https://arxiv.org/abs/2304.08101 `_ - Reference code: `https://github.com/mansang127/LLA-Flow `_ - Model names: ``llaflow``, ``llaflow_raft`` MaskFlownet ----------- `[source code] `__ - Paper: **MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask** - `https://arxiv.org/abs/2003.10955 `_ - Reference code: `https://github.com/cattaneod/MaskFlownet-Pytorch `__ - Model names: ``maskflownet``, ``maskflownet_s`` MatchFlow --------- `[source code] `__ - Paper: **Rethinking Optical Flow from Geometric Matching Consistent Perspective** - `https://arxiv.org/abs/2303.08384 `_ - Reference code: `https://github.com/DQiaole/MatchFlow `_ - Model names: ``matchflow``, ``matchflow_raft`` MemFlow ------- `[source code] `__ - Paper: **MemFlow: Optical Flow Estimation and Prediction with Memory** - `https://arxiv.org/abs/2404.04808 `_ - Reference code: `https://github.com/DQiaole/MemFlow `_ - Model names: ``memflow``, ``memflow_t`` MS-RAFT+ -------- `[source code] `__ - Paper: **High-Resolution Multi-Scale RAFT** - `https://arxiv.org/abs/2210.16900 `_ - Reference code: `https://github.com/cv-stuttgart/MS_RAFT_plus `_ - Model names: ``ms_raft_p`` NeuFlow v1 ---------- `[source code] `__ - Paper: **NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices** - `https://arxiv.org/abs/2403.10425 `_ - Reference code: `https://github.com/neufieldrobotics/neuflow `_ - Model names: ``neuflow`` NeuFlow v2 ---------- `[source code] `__ - Paper: **NeuFlow v2: Push High-Efficiency Optical Flow To the Limit** - `https://arxiv.org/abs/2408.10161 `_ - Reference code: `https://github.com/neufieldrobotics/NeuFlow_v2 `_ - Model names: ``neuflow2`` PWCNet ------ `[source code] `__ - Paper: **PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume** - `https://arxiv.org/abs/1709.02371 `_ - Reference code: `https://github.com/NVlabs/PWC-Net `_ - Model names: ``pwcnet``, ``pwcnet_nodc`` RAFT ---- `[source code] `__ - Paper: **RAFT: Recurrent All-Pairs Field Transforms for Optical Flow** - `https://arxiv.org/abs/2003.12039 `_ - Reference code: `https://github.com/princeton-vl/RAFT `_ - Model names: ``raft``, ``raft_small`` RAPIDFlow --------- `[source code] `__ - Paper: **RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation** - `https://hmorimitsu.com/publication/2024-icra-rapidflow/ `_ - Model names: ``rapidflow``, ``rapidflow_it1``, ``rapidflow_it2``, ``rapidflow_it3``, ``rapidflow_it6``, ``rapidflow_it12`` RPKNet ------ `[source code] `__ - Paper: **Recurrent Partial Kernel Network for Efficient Optical Flow Estimation** - `https://hmorimitsu.com/publication/2024-aaai-rpknet `_ - Model names: ``rpknet`` ScopeFlow --------- `[source code] `__ - Paper: **ScopeFlow: Dynamic Scene Scoping for Optical Flow** - `https://arxiv.org/abs/2002.10770 `_ - Reference code: `https://github.com/avirambh/ScopeFlow `_ - Model names: ``scopeflow`` SCV --- `[source code] `__ - Paper: **Learning Optical Flow from a Few Matches** - `https://arxiv.org/abs/2104.02166 `_ - Reference code: `https://github.com/zacjiang/SCV `_ - Model names: ``scv4``, ``scv8`` SEA-RAFT -------- `[source code] `__ - Paper: **SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow** - `https://arxiv.org/abs/2405.14793 `_ - Reference code: `https://github.com/princeton-vl/SEA-RAFT `_ - Model names: ``sea_raft``, ``sea_raft_s``, ``sea_raft_m``, ``sea_raft_l`` SeparableFlow ------------- `[source code] `__ - Paper: **Separable Flow: Learning Motion Cost Volumes for Optical Flow Estimation** - `https://openaccess.thecvf.com/content/ICCV2021/papers/Zhang_Separable_Flow_Learning_Motion_Cost_Volumes_for_Optical_Flow_Estimation_ICCV_2021_paper.pdf `_ - Reference code: `https://github.com/feihuzhang/SeparableFlow `_ - Model names: ``separableflow`` SKFlow ------ `[source code] `__ - Paper: **SKFlow: Learning Optical Flow with Super Kernels** - `https://arxiv.org/abs/2205.14623 `_ - Reference code: `https://github.com/littlespray/SKFlow `_ - Model names: ``skflow`` SplatFlow --------- `[source code] `__ - Paper: **SplatFlow: Learning Multi-frame Optical Flow via Splatting** - `https://arxiv.org/abs/2306.08887 `_ - Reference code: `https://github.com/wwsource/SplatFLow `_ - Model names: ``splatflow`` STaRFlow -------- `[source code] `__ - Paper: **STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation** - `https://arxiv.org/abs/2007.05481 `_ - Reference code: `https://github.com/pgodet/star_flow `_ - Model names: ``starflow`` VCN --- `[source code] `__ - Paper: **Volumetric Correspondence Networks for Optical Flow** - `https://papers.nips.cc/paper/2019/file/bbf94b34eb32268ada57a3be5062fe7d-Paper.pdf `_ - Reference code: `https://github.com/gengshan-y/VCN `_ - Model names: ``vcn``, ``vcn_small`` VideoFlow --------- `[source code] `__ - Paper: **Videoflow: Exploiting temporal cues for multi-frame optical flow estimation** - `https://arxiv.org/abs/2303.08340 `_ - Reference code: `https://github.com/XiaoyuShi97/VideoFlow `_ - Model names: ``videoflow_bof``, ``videoflow_mof``