Research map / Vision-language and multimodal / Cross-modal learning
Promoting Single-Modal Optical Flow Network for Diverse Cross-Modal Flow Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 ColorJitter augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.955 -> 0.889 | Helped |
| Add ChannelJitter augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.938 -> 0.889 | Helped |
| Add ColorInvert augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.943 -> 0.889 | Helped |
| Add GradualJittier augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.914 -> 0.889 | Helped |
| Add Noise augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.967 -> 0.889 | Helped |
| Add Sharpen augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.977 -> 0.889 | Helped |
| Add Blur augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.892 -> 0.889 | Helped |
| Add Occlusion augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 1.062 -> 0.889 | Helped |
| Add Weather augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.925 -> 0.889 | Helped |
| Add Compression Noise augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.941 -> 0.889 | Helped |
| Add Solarize augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.972 -> 0.889 | Helped |
| Add GlassBlur augmentation (ablation) | MPF · RGBNIR-Stereo | Mean Disparity Error: 0.967 -> 0.889 | Helped |
Closest papers by meaning
- Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution (CVPR 2025 · similarity 0.88)
- Multi-Modal Synergistic Implicit Image Enhancement for Efficient Optical Flow Estimation (CVPR 2025 · similarity 0.87)
- Cross Flow: One-Step Generation Across Latent and Pixel Spaces (NeurIPS 2026 · similarity 0.86)
- Self-Supervised Spatial Correspondence Across Modalities (CVPR 2025 · similarity 0.84)
- StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences (NeurIPS 2024 · similarity 0.84)
- Variational Rectified Flow Matching (ICML 2025 · similarity 0.84)
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.