Research map / Video / Video segmentation and tracking
PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View
Longliang Liu, Miaojie Feng, Junda Cheng, Jijun Xiang, Xuan Zhu, Xin Yang
Read the paperCheck 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 |
|---|---|---|---|
| add orthogonal view with DCCL (ablation) | RAFT baseline · MPFDataset EFT | EPE (px): 4.49 -> 4.32 | Improved |
| add ODDC on top of orthogonal view and DCCL (ablation) | PriOr-RAFT · MPFDataset EFT | EPE (px): 4.32 -> 3.30 | Improved |
| add ODDC (ablation) | PriOr-RAFT · MPFDataset EFT polar regions | EPE (px): 7.56 -> 5.57 | Improved |
| add ODDC (ablation) | PriOr-RAFT · MPFDataset EFT equator | EPE (px): 1.08 -> 1.03 | No clear effect |
| add confidence guidance (warp and group-wise correlation) in ODDC (ablation) | PriOr-RAFT · MPFDataset EFT | EPE (px): 3.36 -> 3.30 | Improved |
| use warp and group-wise correlation confidence instead of fixed distortion map (ablation) | PriOr-RAFT · MPFDataset EFT | EPE (px): 3.34 -> 3.30 | Improved |
| use 90 degree x-axis rotation instead of 90 degree y-axis rotation (ablation) | PriOr-RAFT · MPFDataset EFT | EPE (px): 3.55 -> 3.30 | Improved |
| use 90 degree instead of 45 degree x-axis rotation (ablation) | PriOr-RAFT · MPFDataset EFT | EPE (px): 3.41 -> 3.30 | Improved |
| apply PriOr-Flow to GMA (ablation) | GMA · MPFDataset EFT | EPE (px): 4.26 -> 3.25 | Improved |
| apply PriOr-Flow to SKFlow (ablation) | SKFlow · MPFDataset EFT | EPE (px): 3.79 -> 3.19 | Improved |
| reduce iterations to 4 in PriOr-RAFT (ablation) | PriOr-RAFT · MPFDataset EFT | EPE (px): 4.49 -> 3.89 | Improved |
| add PriOr-Flow with only 3 iterations (ablation) | RAFT · MPFDataset EFT | EPE (px): 4.49 -> 4.37 | Improved |
Closest papers by meaning
- PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation (ICML 2026 · similarity 0.88)
- SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data (ECCV 2026 · similarity 0.87)
- Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation (TPAMI 2019 · similarity 0.87)
- PanFlow: Decoupled Motion Control for Panoramic Video Generation (AAAI 2026 · similarity 0.87)
- StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences (NeurIPS 2024 · similarity 0.87)
- DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework (CVPR 2025 · 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.
