Research map / Label-efficient and robust learning / Recognition and long-tail
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun
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 |
|---|---|---|---|
| Use UPFlow rather than ARFlow | unsupervised optical flow estimation · KITTI 2012 test | EPE: 1.8 -> 1.4 | Improved |
| Use UPFlow rather than UFlow | unsupervised optical flow estimation · KITTI 2015 test | F1-all: 11.13% -> 9.38% | Improved |
| Add SGU to the model with CL, BDWL, and ARL (ablation) | UPFlow · KITTI 2015 train | EPE ALL: 2.64 -> 2.56 | Improved |
| Add PDL to the model with CL, BDWL, and ARL (ablation) | UPFlow · KITTI 2015 train | EPE ALL: 2.64 -> 2.61 | Improved |
| Add SGU to the model with CL, BDWL, and ARL (ablation) | UPFlow · Sintel Clean train | EPE ALL: (2.61) -> (2.46) | Improved |
| Add PDL to the model with CL, BDWL, and ARL (ablation) | UPFlow · Sintel Final train | EPE ALL: (3.17) -> (2.93) | Improved |
| Add both SGU and PDL (ablation) | UPFlow with CL, BDWL, and ARL · Sintel Clean train | EPE ALL: (2.61) -> (2.33) | Improved |
| Add SGU interpolation flow and interpolation map (ablation) | SGU-FM · KITTI 2012 | EPE: 1.35 -> 1.27 | Improved |
| Add the SGU interpolation map (ablation) | SGU-M · KITTI 2012 | EPE: 1.33 -> 1.27 | Improved |
| Replace bilinear upsampling with SGU (ablation) | UPFlow · KITTI 2012 | EPE: 1.36 -> 1.27 | Improved |
| Replace no pyramid loss with PDL (ablation) | UPFlow · Sintel Clean train x1 | EPE: (2.46) -> (2.33) | Improved |
| Replace PDL with pyramid unsupervised loss at intermediate resolution (ablation) | UPFlow · Sintel Clean train x1 | EPE: (2.33) -> (2.49) | Hurt |
Closest papers by meaning
- Unsupervised Deep Learning for Optical Flow Estimation (AAAI 2017 · similarity 0.89)
- UnFlow: Unsupervised Learning of Optical Flow With a Bidirectional Census Loss (AAAI 2018 · similarity 0.89)
- DDFlow: Learning Optical Flow with Unlabeled Data Distillation (AAAI 2019 · similarity 0.89)
- DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework (CVPR 2025 · similarity 0.87)
- UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR 2024 · similarity 0.86)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · similarity 0.86)
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.
