Topology-Preserving Data Augmentation for Ring-Type Polygon Annotations

Abstract

Geometric data augmentation is widely used in segmentation pipelines and typically assumes that polygon annotations represent simply connected regions. However, in structured domains such as architectural floorplan analysis, ring-type regions are often encoded as a single cyclic polygon chain connecting outer and inner boundaries. During augmentation, clipping operations may remove intermediate vertices and disrupt this cyclic connectivity, breaking the structural relationship between the boundaries. In this work, we introduce an order-preserving polygon augmentation strategy that performs transformations in mask space and then projects surviving vertices back into index-space to restore adjacency relations. This repair maintains the original traversal order of the polygon and preserves topological consistency with minimal computational overhead. Experiments demonstrate that the approach reliably restores connectivity, achieving near-perfect Cyclic Adjacency Preservation (CAP) across both single and compound augmentations.

Figures (6)

• Figure 1: Failure of ring-type polygon annotations under geometric augmentation. Left: Ground-truth polygon with a narrow bridge connector and inner boundaries are shown in red color and outer boundary in green color. Each corner has a vertex(keypoints), and mask (olive color) shows ring type annotation generated because of wall design. Middle and Right: Representative failure cases after augmentation, where the connector is disrupted and the polygon topology is no longer preserved, yielding separate outer mask from outer boundary and inner boundary masks from inner boundary mask.
• Figure 2: Overview of the proposed topology-preserving augmentation pipeline for ring-type polygons. From left to right: the input ring region is encoded as a single cyclic polygon chain $P=(p_1,\dots,p_n)$ representing outer and inner boundaries. The polygon is rasterized and geometric augmentation is applied in mask space, $M' = T(M)$ (e.g., rotate, crop, scale, translate). The surviving polygon indices are then projected in order and successor consistency is checked. If the order is preserved, the polygon remains valid; otherwise, gaps in the index sequence are repaired using the proposed index-space reconnection method. The resulting polygon $\hat{P}$ forms a single closed cyclic chain with preserved ring topology.
• Figure 3: Vertex projection after mask-based augmentation. The dashed blue polygon shows the original vertex sequence with indices, while the solid orange polygon shows the augmented polygon. Surviving vertices are projected onto the augmented boundary and retain their original indices, preserving the cyclic ordering of the polygon chain. Vertices removed by clipping are discarded, allowing the augmented polygon to be reconstructed while maintaining index consistency.
• Figure 4: Qualitative results using Roboflow augmentation. The left panel shows the ground truth polygon with a ring structure. The middle and right panels illustrate failure cases after augmentation, where clipping and rotation remove the bridge connection between the outer and inner boundaries. As a result, the original ring polygon becomes fragmented and is incorrectly represented as two independent polygons corresponding to the outer and inner regions.
• Figure 5: Examples illustrating topology failure under YOLO training augmentation with default parameters. The upper row shows the ground truth ring-type polygon annotations, while the lower row shows the augmented outputs. After augmentation, the interior hole is lost and the region is incorrectly represented as a single large polygon, breaking the intended ring topology.