Research map / Detection and segmentation / CNN features

TopoRefine: Plug-and-Play Topology-Aware Contour Refinement for Building Segmentation

NeurIPS 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation

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.

Proposes TopoRefine, a plug-and-play topology-aware contour refinement module that converts SAM-style pixel masks of buildings into geometrically regular contours.

Problem

SAM-style building segmentation yields pixel-wise masks with fragmented regions and irregular boundaries, so direct contour vectorization is unreliable and geometric regularity of buildings is lost.

Approach

A plug-and-play, topology-aware contour refinement step applied on top of foundation segmentation model (SAM-style) masks to restore geometric regularity for building vectorization; the abstract is truncated so specifics beyond this are not stated.

Experimental setup

Builds on: SAM

Closest papers by meaning

• Joint Semantic-geometric Learning for Polygonal Building Segmentation (AAAI 2021 · similarity 0.88)
• Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.86)
• GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation (AAAI 2025 · similarity 0.86)
• HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild (NeurIPS 2025 · similarity 0.85)
• CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction (NeurIPS 2025 · similarity 0.85)
• SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.84)