Optical Flow Estimation
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
Papers
Showing 1–10 of 2184 papers
All datasetsSintel-cleanSintel-finalKITTI 2015 (train)KITTI 2015KITTI 2012SpringSintel Clean unsupervisedSintel Final unsupervisedKITTI 2015 unsupervisedKITTI 2012 unsupervised
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FastFlowNet-ft | Average End-Point Error | 1.8 | — | Unverified |
| 2 | IRR-PWC | Average End-Point Error | 1.6 | — | Unverified |
| 3 | LiteFlowNet-ft | Average End-Point Error | 1.6 | — | Unverified |
| 4 | SelFlow | Average End-Point Error | 1.5 | — | Unverified |
| 5 | PWC-Net + ft - axXiv | Average End-Point Error | 1.5 | — | Unverified |
| 6 | FDFlowNet-ft | Average End-Point Error | 1.5 | — | Unverified |
| 7 | LiteFlowNet2-ft | Average End-Point Error | 1.4 | — | Unverified |
| 8 | LiteFlowNet3 | Average End-Point Error | 1.3 | — | Unverified |
| 9 | LiteFlowNet3-S | Average End-Point Error | 1.3 | — | Unverified |
| 10 | MaskFlownet | Average End-Point Error | 1.1 | — | Unverified |