Research map / Graph learning / Graph self-supervised learning
VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction, Characterization and Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
The paper proposes VisDiff, an SDF-guided polygon generation approach for reconstructing, characterizing, and recognizing visibility structures (visibility graphs/polygons), targeting combinatorial structures lacking well-defined features or distance metrics.
Problem
Machine learning on combinatorial structures that lack well-defined features, neighborhoods, or distance metrics, specifically visibility structures such as polygons and their visibility graphs.
Approach
Uses signed distance function (SDF) guidance to generate polygons whose visibility structure matches a target, enabling reconstruction, characterization, and recognition of visibility graphs. Details beyond the abstract are not stated.
Closest papers by meaning
- PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models (NeurIPS 2023 · similarity 0.87)
- ViLearn: Accelerating Training Convergence of Image-to-3D Generation via Visibility Learning (CVPR 2026 · similarity 0.86)
- PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph (ICLR 2025 · similarity 0.85)
- Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features (CVPR 2024 · similarity 0.85)
- Hyperbolic Geometric Latent Diffusion Model for Graph Generation (ICML 2024 · similarity 0.84)
- Feat2GS: Probing Visual Foundation Models with Gaussian Splatting (CVPR 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.