paper-with-me

Optical Flow Estimation 벤치마크

Optical Flow Estimation on Sintel-final

28개 결과 · ⬇ CSV · JSON

Average End-Point Error 낮을수록 좋음

1.907 3.52 5.133 6.747 8.36 2016-11 2026-11 Spynet — 8.36 (2016-11-03) MR-Flow — 5.38 (2017-05-03) LiteFlowNet-ft — 5.38 (2018-05-18) ContinualFlow + ft — 4.52 (2018-11-05) LiteFlowNet2-ft — 4.69 (2019-03-15) IRR-PWC — 4.579 (2019-04-10) SelFlow — 4.26 (2019-04-19) VCN — 4.4 (2019-12-01) ScopeFlow — 4.098 (2020-02-25) MaskFlownet — 4.17 (2020-03-24) MaskFlownet-S — 4.38 (2020-03-24) RAFT (warm-start) — 2.855 (2020-03-26) FDFlowNet-ft — 5.11 (2020-06-22) LiteFlowNet3 — 4.45 (2020-07-18) LiteFlowNet3-S — 4.53 (2020-07-18) UnrolledCost — 5.8 (2020-11-30) FastFlowNet-ft — 6.08 (2021-03-08) GMA — 2.47 (2021-04-06) Perceiver IO — 2.42 (2021-07-30) GMFlowNet — 2.648 (2022-03-21) DEQ-Flow-H — 2.886 (2022-04-18) GMFlow — 2.37 (2022-11-10) CroCo-Flow — 2.436 (2022-11-18) Ef-RAFT — 2.6 (2024-01-01) RPKNet — 2.657 (2024-02-01) RAPIDFlow — 3.56 (2024-05-01) DPFlow — 1.975 (2025-03-19) MEMFOF-L — 1.907 (2025-06-29) Spynet — 8.36 (2016-11-03) MR-Flow — 5.38 (2017-05-03) ContinualFlow + ft — 4.52 (2018-11-05) SelFlow — 4.26 (2019-04-19) ScopeFlow — 4.098 (2020-02-25) RAFT (warm-start) — 2.855 (2020-03-26) GMA — 2.47 (2021-04-06) Perceiver IO — 2.42 (2021-07-30) GMFlow — 2.37 (2022-11-10) DPFlow — 1.975 (2025-03-19) MEMFOF-L — 1.907 (2025-06-29)
RankModel Average End-Point Error PaperCodeYear
1 MEMFOF-L 1.907 MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation msu-video-group/memfof 2025
2 DPFlow 1.975 DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework hmorimitsu/ptlflow 2025
3 GMFlow 2.37 Unifying Flow, Stereo and Depth Estimation autonomousvision/unimatch 2022
4 Perceiver IO 2.42 Perceiver IO: A General Architecture for Structured Inputs & Outputs huggingface/transformers · deepmind/deepmind-research · lucidrains/perceiver-pytorch · +6 2021
5 CroCo-Flow 2.436 CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow naver/croco 2022
6 GMA 2.470 Learning to Estimate Hidden Motions with Global Motion Aggregation open-mmlab/mmflow · zacjiang/GMA 2021
7 Ef-RAFT 2.60 Rethinking RAFT for Efficient Optical Flow n3slami/Ef-RAFT 2024
8 GMFlowNet 2.648 Global Matching with Overlapping Attention for Optical Flow Estimation xiaofeng94/gmflownet 2022
9 RPKNet 2.657 Recurrent Partial Kernel Network for Efficient Optical Flow Estimation hmorimitsu/ptlflow 2024
10 RAFT (warm-start) 2.855 RAFT: Recurrent All-Pairs Field Transforms for Optical Flow pytorch/vision · princeton-vl/RAFT · open-mmlab/mmflow · +14 2020
11 DEQ-Flow-H 2.886 Deep Equilibrium Optical Flow Estimation locuslab/deq-flow 2022
12 RAPIDFlow 3.56 RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation hmorimitsu/ptlflow 2024
13 ScopeFlow 4.098 ScopeFlow: Dynamic Scene Scoping for Optical Flow avirambh/ScopeFlow 2020
14 MaskFlownet 4.17 MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask open-mmlab/mmflow · microsoft/MaskFlownet · AMatusV/MaskFlownet-ROS 2020
15 SelFlow 4.26 SelFlow: Self-Supervised Learning of Optical Flow ppliuboy/SelFlow 2019
16 MaskFlownet-S 4.38 MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask open-mmlab/mmflow · microsoft/MaskFlownet · AMatusV/MaskFlownet-ROS 2020
17 VCN 4.40 Volumetric Correspondence Networks for Optical Flow gengshan-y/VCN · neu-vig/ezflow 2019
18 LiteFlowNet3 4.45 LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation twhui/LiteFlowNet3 2020
19 ContinualFlow + ft 4.52 Continual Occlusions and Optical Flow Estimation 2018
20 LiteFlowNet3-S 4.53 LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation twhui/LiteFlowNet3 2020
1–20 / 28 다음 → 페이지당 10 20 50 100