Research map / Label-efficient and robust learning / Recognition and long-tail
Unsupervised Deep Learning for Optical Flow Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| unsupervised training on unlabeled KITTI multi-view frames instead of synthetic Chairs (ablation) | DSTFlow · KITTI2015 train | fl-all: 0.52 -> 0.36 | Helped |
| unsupervised DSTFlow vs supervised FlowNet | optical flow CNN · KITTI2012 test noc | EPE: 5.0 -> 4.0 | Helped |
| unsupervised DSTFlow vs supervised FlowNet | optical flow CNN · Sintel Final test occ | EPE: 7.76 -> 11.28 | Hurt |
| Chairs pretraining before KITTI unsupervised finetuning (ablation) | DSTFlow(KITTI) · KITTI2015 train | fl-all: 0.36 -> 0.48 | Hurt |
| Chairs pretraining before Sintel finetuning (ablation) | DSTFlow(Sintel) · Sintel Final test occ | EPE: 11.28 -> 11.27 | No clear effect |
| unsupervised DSTFlow vs learning-free LDOF | optical flow · KITTI2012 test noc | EPE: 5.6 -> 4.0 | Helped |
Closest papers by meaning
- Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation (CVPR 2020 · similarity 0.92)
- UnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss (AAAI 2018 · similarity 0.92)
- Learning Optical Flow From Still Images (CVPR 2021 · similarity 0.91)
- Recurrent Partial Kernel Network for Efficient Optical Flow Estimation (AAAI 2024 · similarity 0.89)
- UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR 2024 · similarity 0.88)
- FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models (CVPR 2024 · similarity 0.87)
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.