Research map / Learning theory and algorithms / Clustering
Manifold SLIC: A Fast Method to Compute Content-Sensitive Superpixels
Check 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 |
|---|---|---|---|
| Use manifold-area-based restricted CVT to make superpixels content-sensitive | Manifold SLIC · BSDS500 | under segmentation error | Helped |
| Use manifold-area-based restricted CVT to make superpixels content-sensitive | Manifold SLIC · BSDS500 | boundary recall | Helped |
| Use manifold-area-based restricted CVT to make superpixels content-sensitive | Manifold SLIC · BSDS500 | achievable segmentation accuracy | Helped |
| Use manifold-area-based restricted CVT and local search instead of SSS geodesic-distance computation | Manifold SLIC · BSDS500 | runtime: 10 times faster | Helped |
| Replace local search with global search (ablation) | Manifold SLIC · BSDS500 | under segmentation error | No clear effect |
| Replace local search with global search (ablation) | Manifold SLIC · BSDS500 | boundary recall | No clear effect |
| Replace local search with global search (ablation) | Manifold SLIC · BSDS500 | achievable segmentation accuracy | No clear effect |
| Add splitting and merging operators (ablation) | Manifold SLIC · BSDS500 | under segmentation error | Helped |
| Add splitting and merging operators (ablation) | Manifold SLIC · BSDS500 | boundary recall | Helped |
| Add splitting and merging operators (ablation) | Manifold SLIC · BSDS500 | achievable segmentation accuracy | Helped |
Closest papers by meaning
- Superpixels and Polygons Using Simple Non-Iterative Clustering (CVPR 2017 · similarity 0.90)
- Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds (CVPR 2018 · similarity 0.87)
- Differentiable Laplacian Matrix Guided Superpixel Segmentation (CVPR 2026 · similarity 0.85)
- Learning Invariant Inter-pixel Correlations for Superpixel Generation (AAAI 2024 · similarity 0.85)
- Learning the Superpixel in a Non-Iterative and Lifelong Manner (CVPR 2021 · similarity 0.85)
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction (NeurIPS 2025 · 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.