Research map / 3D vision / Depth and stereo
OF-MSRN: Optical Flow-Auxiliary Multi-Task Regression Network for Direct Quantitative Measurement, Segmentation and Motion Estimation
Chengqian Zhao, Cheng Feng, Dengwang Li, Shuo Li
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 optical flow auxiliary module (and bidirectional OF) to MSRN (ablation) | OF-MSRN · Carotid US, CALD | MAE (pixel): 2.38 -> 1.23 | Improved |
| add optical flow auxiliary module to MSRN (ablation) | OF-MSRN · Carotid US, CIMT | MAE (pixel): 1.57 -> 0.93 | Improved |
| add optical flow auxiliary module to MSRN (ablation) | OF-MSRN · Carotid US, CALD | IoU: 0.869 -> 0.908 | Improved |
| add optical flow auxiliary module to MSRN (ablation) | OF-MSRN · Carotid US, CIMT | IoU: 0.874 -> 0.893 | Improved |
| add segmentation task and OFA to measurement-only regression (MRNns) (ablation) | OF-MSRN · Carotid US, CALD | MAE (pixel): 1.47 -> 1.23 | Improved |
| add multi-scale feature encoder with multi-task regression versus plain MFE regression (ablation) | OF-MSRN · Carotid US, CALD | MAE (pixel): 5.21 -> 1.23 | Improved |
| jointly regress measurement and segmentation with OFA instead of OF-FCN segmentation only | OF-MSRN · Carotid US, CIMT | IoU: 0.781 -> 0.893 | Improved |
| use MFE encoder instead of ResNet101 regression | regression baseline · Carotid US, CALD | MAE (pixel): 10.94 -> 5.21 | Improved |
Closest papers by meaning
- RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation (NeurIPS 2023 · similarity 0.85)
- Blood Flow Speed Estimation with Optical Coherence Tomography Angiography Images (CVPR 2025 · similarity 0.83)
- vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation (CVPR 2025 · similarity 0.81)
- GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images (AAAI 2025 · similarity 0.81)
- DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation (CVPR 2025 · similarity 0.81)
- Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy (AAAI 2025 · similarity 0.80)
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.
