Research map / Learning theory and algorithms / Optimal transport
Computing Wasserstein-p Distance Between Images With Linear Cost
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 |
|---|---|---|---|
| Restrict Sinkhorn iterations to a multi-scale estimated subset | M3S · DOT, grayscale image transport | solving time: 28.90 seconds for 512 × 512 images; other methods fail to converge within 1200 seconds | Helped |
| Use restricted multi-scale sparse transport instead of a full dense coupling | M3S · DOT, grayscale image transport | memory complexity: O(n2) -> linear | Helped |
| Use restricted multi-scale sparse transport instead of full Sinkhorn | M3S · DOT, grayscale image transport | time complexity: O(n2) -> linear | Helped |
| Use M3S to approximate the unregularized transport solution | M3S · DOT, grayscale images, p values 1 to 2 | relative error: Table 1 reports relative errors from 0.0522 to 6.23 (10−4) | Helped |
| Compute transport on the restricted subset across image scales | M3S · Color images up to 1920 × 1200 | image size supported: 1920 × 1200 | Helped |
Closest papers by meaning
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 2024 · similarity 0.86)
- Scalable Approximation Algorithms for $p$-Wasserstein Distance and Its Variants (ICML 2025 · similarity 0.86)
- Tree-Sliced Wasserstein Distance: A Geometric Perspective (ICML 2025 · similarity 0.85)
- Distance-Based Tree-Sliced Wasserstein Distance (ICLR 2025 · similarity 0.85)
- Linear Partial Gromov-Wasserstein Embedding (ICLR 2025 · similarity 0.84)
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (ICML 2024 · 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.