Research map / 3D vision / Depth and stereo
Superpixel-Guided Two-View Deterministic Geometric Model Fitting
Guobao Xiao, Hanzi Wang, Yan Yan, David Suter
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 model hypothesis updating strategy (SDF2 -> SDF3) (ablation) | SDF · Single-structure homography, Graffiti | average fitting error (%): 16.51 -> 4.71 | Improved |
| add model hypothesis updating strategy (SDF2 -> SDF3) (ablation) | SDF · Single-structure homography, Trees | average fitting error (%): 31.68 -> 11.88 | Improved |
| add model hypothesis updating strategy (SDF2 -> SDF3) (ablation) | SDF · Single-structure homography, Unionhouse | average fitting error (%): 38.55 -> 0.30 | Improved |
| add model hypothesis updating strategy (SDF2 -> SDF3) (ablation) | SDF · Single-structure fundamental matrix, Cube | average fitting error (%): 8.94 -> 1.32 | Improved |
| add model hypothesis updating strategy (SDF2 -> SDF3) (ablation) | SDF · Single-structure fundamental matrix, Biscuit | average fitting error (%): 5.45 -> 0.90 | Improved |
| add model hypothesis updating strategy (SDF2 -> SDF3) (ablation) | SDF · Single-structure fundamental matrix, Corridor | average fitting error (%): 9.87 -> 3.70 | Improved |
| add improved model selection (SDF1 -> SDF2) (ablation) | SDF · Single-structure homography, Graffiti | average fitting error (%): 24.05 -> 16.51 | Improved |
| add improved model selection (SDF1 -> SDF2) (ablation) | SDF · Single-structure homography, Trees | average fitting error (%): 37.62 -> 31.68 | Improved |
| add improved model selection (SDF1 -> SDF2) (ablation) | SDF · Single-structure fundamental matrix, Cube | average fitting error (%): 7.28 -> 8.94 | Hurt |
| add improved model selection (SDF1 -> SDF2) (ablation) | SDF · Single-structure fundamental matrix, Biscuit | average fitting error (%): 5.45 -> 5.45 | No clear effect |
| use SDF3 instead of RANSAC/PROSAC/T-linkage/RansaCov on multi-structure data | SDF3 · Multi-structure homography, Elderhallb | average fitting error (%): 11.54 -> 3.33 | Improved |
| use SDF3 instead of T-linkage | SDF3 · Multi-structure fundamental matrix, Breadtoycar | average fitting error (%): 4.42 -> 6.74 | Hurt |
Closest papers by meaning
- Superpixel-Based Two-View Deterministic Fitting for Multiple-Structure Data (ECCV 2016 · similarity 0.97)
- Efficient Deterministic Search with Robust Loss Functions for Geometric Model Fitting (TPAMI 2021 · similarity 0.87)
- Geometric Multi-Model Fitting With a Convex Relaxation Algorithm (CVPR 2018 · similarity 0.85)
- Bayesian Adaptive Superpixel Segmentation (ICCV 2019 · similarity 0.84)
- PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence (TPAMI 2016 · similarity 0.83)
- PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus (AAAI 2024 · similarity 0.82)
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.
