Font Generation Consistency via Depth Map Noise Preprocessing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems face challenges in generating custom art fonts with consistent style while requiring fewer computing resources, as they often involve extra steps like style extraction and injection, which increase computational demands.

Innovation Solution

A font generation system that preprocesses depth maps by adding noise, then uses a generative image model to generate custom font images based on a text prompt and the preprocessed depth maps, ensuring consistent style across characters with reduced computational requirements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If style extraction and injection methods are used to improve style consistency, then style consistency is improved, but computational requirements significantly increase

Engineering Contradiction:

Improvestyle consistencyVSAvoidcomputational requirements

Core Design Contradiction:

Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies preliminary action by pre-processing depth maps with noise addition before they are fed to the generative model. This preprocessing step establishes a consistent foundation for all character generations, ensuring style consistency is achieved during the single generation pass rather than requiring post-generation style extraction and injection operations.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent extracts and removes the style extraction and injection steps from the traditional multi-step process. By integrating style consistency directly into the depth map pre-processing and single generation pass, the system eliminates the need for separate style extraction and injection operations, thereby reducing computational requirements while maintaining style consistency.

Inventive Principle:

Principle #2Taking out (Extraction)

2Manufacturing precision

If multiple processing steps (style generation, extraction, injection) are used to achieve style consistency, then style consistency is improved, but device complexity increases

Engineering Contradiction:

Improvestyle consistencyVSAvoidprocess complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent merges multiple separate processing steps (style generation, style extraction, and style injection) into a single integrated generation pass. By combining these operations and achieving style consistency through pre-processed depth maps and conditional generation, the system reduces process complexity from multiple sequential steps to a unified workflow.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The generative image model serves multiple functions simultaneously: it generates character images while maintaining style consistency, processes depth maps with noise, and applies text prompt conditions all in one operation. This multi-functionality eliminates the need for separate dedicated steps for each processing task, thereby reducing overall device and process complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250078343A1Control font generation consistency

Publication Date: 2025.03.06 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Systems and methods for generating custom art fonts with consistent style include receiving user input that identifies a base font style for a custom font and includes descriptive text that defies one or more text effects to use for the custom font. Depth maps are selected for characters to be included in the custom font. The depth maps are preprocessed to add noise to the depth maps. A generative model generates custom font images conditioned with the text prompt and the depth maps. The custom font images are then used to render text on a display screen of a computing device.