Research map / Label-efficient and robust learning / Recognition and long-tail
MaskFlownet: Asymmetric Feature Matching With Learnable Occlusion Mask
Shengyu Zhao, Yilun Sheng, Yue Dong, Eric I-Chao Chang, Yan Xu
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace standard FMM with OFMM using a learnable mask and trade-off term (ablation) | MaskFlownet-S · Sintel clean and final validation, Chairs-trained | AEPE: 3.02 -> 3.06 (clean); 4.70 -> 4.52 (final) | Mixed |
| use asymmetric deformable feature matching instead of symmetric FMM (ablation) | MaskFlownet-S · Sintel clean and final validation, Chairs-trained | AEPE: 3.02 -> 2.70 (clean); 4.70 -> 4.07 (final) | Improved |
| add symmetric convolution to OFMM (ablation) | OFMM · Sintel clean and final train, Chairs-trained | AEPE: 3.20 -> 3.33 (clean); 4.50 -> 4.64 (final) | Hurt |
| add asymmetric convolution before warping (ablation) | OFMM · Sintel clean and final train, Chairs-trained | AEPE: 3.20 -> 2.96 (clean); 4.50 -> 4.29 (final) | Improved |
| replace warping and extra convolution with deformable convolution (ablation) | OFMM · Sintel clean and final train, Chairs-trained | AEPE: 3.20 -> 2.88 (clean); 4.50 -> 4.25 (final) | Improved |
| add both the learnable mask and trade-off term (ablation) | AsymOFMM · Sintel clean train, Chairs-trained | AEPE: 3.08 -> 2.88 | Improved |
| add the learnable mask without the trade-off term (ablation) | AsymOFMM · Sintel clean and final train, Chairs-trained | AEPE: 3.08 -> 3.06 (clean); 4.29 -> 4.32 (final) | Hurt |
| add the trade-off term without the learnable mask (ablation) | AsymOFMM · Sintel clean and final train, Chairs-trained | AEPE: 3.08 -> 2.97 (clean); 4.29 -> 4.30 (final) | Mixed |
| cascade using a single new feature pyramid without mask (ablation) | MaskFlownet-S · Sintel val clean and final | AEPE: 2.70 -> 2.53 (clean); 4.07 -> 3.90 (final) | Improved |
| use dual feature pyramids instead of a single pyramid without mask (ablation) | cascaded MaskFlownet · Sintel val clean and final | AEPE: 2.53 -> 2.52 (clean); 3.90 -> 3.85 (final) | Improved |
| concatenate the occlusion mask in the dual-pyramid cascade (ablation) | cascaded MaskFlownet · Sintel val clean and final | AEPE: 2.52 -> 2.52 (clean); 3.85 -> 3.83 (final) | Mixed |
| use MaskFlownet instead of VCN | optical flow estimation · MPI Sintel clean test | AEPE: 2.81 -> 2.52 | Improved |
Later papers that compared with this method
1 later accepted paper reports MaskFlowNet as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation (TPAMI 2021 · better on 1 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SelFlow — SelFlow: Self-Supervised Learning of Optical Flow (CVPR 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation (ICCV 2017 · similarity 0.89)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · similarity 0.88)
- Occlusion Aware Unsupervised Learning of Optical Flow (CVPR 2018 · similarity 0.88)
- UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR 2024 · similarity 0.86)
- OAMaskFlow: Occlusion-Aware Motion Mask for Scene Flow (AAAI 2025 · similarity 0.85)
- DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
