Research map / 3D vision / Depth and stereo
MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene Flow Estimation with Monocular Images
Runfa Li, Truong Nguyen
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 the second decoder level (lev1-lev2) to the last-level decoder (ablation) | MonoPLFlowNet · Flyingthings3D | EPE3D (m): 0.4781 -> 0.4439 | Improved |
| use all three levels of 2D-3D feature alignment instead of the two last levels (ablation) | MonoPLFlowNet · Flyingthings3D | EPE3D (m): 0.4439 -> 0.4248 | Improved |
| use all three levels instead of only the last level (ablation) | MonoPLFlowNet · Flyingthings3D | ACC3DS: 0.4587 -> 0.5099 | Improved |
| use all three levels instead of only the last level (ablation) | MonoPLFlowNet · Flyingthings3D | EPE2D (px): 26.3133 -> 23.7657 | Improved |
| use all three levels instead of only the last level (ablation) | MonoPLFlowNet · Flyingthings3D | Outlier3D: 0.8935 -> 0.8595 | Improved |
| recover Mono-Expansion 3D flow with our depth instead of Mono-SF depth | Mono-Expansion · KITTI flow 2015 | EPE3D (m): 2.7079 -> 1.6673 | Improved |
| train on Flyingthings3D with real-scale MonoPLFlowNet instead of Mono-SF trained on KITTI | depth on Flyingthings3D · Flyingthings3D depth | Abs Rel: 0.943 -> 0.188 | Improved |
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.
- Mono-SF — Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes (ICCV 2019) · better on 9 of 9 shared results
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
- HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Clouds (CVPR 2019 · similarity 0.91)
- Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes (ICCV 2019 · similarity 0.90)
- Self-Supervised Monocular Scene Flow Estimation (CVPR 2020 · similarity 0.90)
- Zero-Shot Monocular Scene Flow Estimation in the Wild (CVPR 2025 · similarity 0.89)
- Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations (CVPR 2025 · similarity 0.87)
- ZeroFlow: Scalable Scene Flow via Distillation (ICLR 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.
