Semantic Vector Hierarchies for Context-Preserving Image Editing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image vectorization systems generate flat, unstructured vector paths from raster images, lacking semantic organization and relational information, leading to inefficiencies and loss of contextual information during conversion.
Innovation Solution
A hierarchical semantic grouping system that organizes vector paths into a nested hierarchy using a semantic object segmentation model to generate object masks and a vector region segmentation model to trace paths, preserving semantic relationships and facilitating efficient editing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If existing systems extract SVGs from raster images, then vector paths are generated, but the extracted SVGs are flat and lack semantic organization
Solution Approach 1:
The patent segments the flat SVG structure into hierarchical groups organized by semantic relationships. Vector paths are divided into parent-child groupings that reflect the spatial and semantic relationships in the original raster image, allowing contextual information to be preserved through structured organization rather than losing it in a flat hierarchy.
Solution Approach 2:
The patent implements nested hierarchical groups where parent groups contain child groups and paths in a nested structure. This nesting preserves the spatial relationships and semantic context from the original image by organizing vector elements in concentric hierarchical layers, with each level representing different scales of semantic organization.
2Productivity
If vector paths are organized hierarchically with semantic grouping, then editing efficiency is enhanced, but system complexity increases
Solution Approach 1:
The patent performs preliminary semantic analysis and hierarchical organization during the initial vectorization process. By pre-establishing the semantic hierarchy and grouping relationships before editing occurs, the system eliminates the need for manual organization during editing, thereby improving editing efficiency despite the increased structural complexity.
Solution Approach 2:
The system automatically performs semantic segmentation and hierarchical grouping without requiring manual intervention. The vectorization algorithm itself services the organization task by automatically creating semantically meaningful groups based on image content analysis, reducing the burden on users while managing the complexity internally.
3Reliability
If semantic object segmentation model is used to generate object masks, then semantic relationships are preserved, but processing time increases
Solution Approach 1:
The patent applies semantic segmentation at selective levels of detail rather than uniformly across all elements. By performing partial semantic analysis on only the most important regions or at coarser resolution levels first, the system preserves semantic accuracy where needed while reducing overall processing time through selective application of the segmentation model.
Data Source
AI summary
The present disclosure is directed toward systems, methods, and non-transitory computer readable media that provide that provide processes and a graphical user interface tailored to organize vector geometry within a vector image into a hierarchical structure based on layered semantic groups. In particular, in one or more embodiments, the disclosed systems determine, using an object segmentation model, a set of masks corresponding to objects depicted within a raster image. The disclosed systems determine an intersection between a first mask and a second mask from among the set of masks. The disclosed systems generate a hierarchical semantic structure comprising a set of nodes corresponding to the set of masks by generating a first node for the first mask and a second node for the second mask arranged according to the intersection. The disclosed systems generate a vector image from the raster image according to the hierarchical semantic structure.