Research map / 3D vision / Depth and stereo
Motion Basis Learning for Unsupervised Deep Homography Estimation With Subspace Projection
Nianjin Ye, Chuan Wang, Haoqiang Fan, Shuaicheng Liu
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 |
|---|---|---|---|
| replace 4-offset regression with homography flow basis weights (ablation) | CA-Unsupervised with mask · CA-Unsupervised homography test (4.2k) ablation (avg) | point matching error (lower is better): 0.88 -> 0.83 | Improved |
| add feature identity loss (FIL) (ablation) | mask + basis network · CA-Unsupervised homography test (4.2k) ablation (avg) | point matching error (lower is better): 0.83 -> 0.77 | Improved |
| replace mask module with LRR blocks (ablation) | homography flow basis network · CA-Unsupervised homography test (4.2k) ablation (avg) | point matching error (lower is better): 0.83 -> 0.60 | Improved |
| add feature identity loss (FIL) (ablation) | LRR + basis network · CA-Unsupervised homography test (4.2k) ablation (avg) | point matching error (lower is better): 0.60 -> 0.50 | Improved |
| add feature extractor f() with 3 conv layers instead of photometric loss only (no FIL) (ablation) | homography estimator · CA-Unsupervised homography test, feature extractor depth | point matching error (lower is better): 0.76 -> 0.60 | Improved |
| increase f() from 2 to 3 layers without FIL (ablation) | homography estimator · CA-Unsupervised homography test, feature extractor depth | point matching error (lower is better): 0.61 -> 0.60 | No clear effect |
| add FIL to 3-layer f() training (ablation) | homography estimator · CA-Unsupervised homography test, feature extractor depth | point matching error (lower is better): 0.60 -> 0.50 | Improved |
| use full BasesHomo instead of strongest feature-based pipeline (SuperPoint + SuperGlue + MAGSAC) | BasesHomo · CA-Unsupervised homography test (4.2k) (avg over 5 scene types) | point matching error: 0.63 -> 0.50 | Improved |
Closest papers by meaning
- Adapting Dense Matching for Homography Estimation with Grid-based Acceleration (CVPR 2025 · similarity 0.88)
- SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization (CVPR 2025 · similarity 0.88)
- MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation (CVPR 2024 · similarity 0.87)
- Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization (NeurIPS 2024 · similarity 0.86)
- Noisy One-point Homographies are Surprisingly Good (CVPR 2024 · similarity 0.86)
- Deep Homography Estimation for Visual Place Recognition (AAAI 2024 · 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.
