Digital Human Clothing Texture Generation for Cross-Species Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies struggle to enhance user experience by effectively personifying target objects, such as pets, in digital humans due to challenges in matching features between different species and ensuring aesthetic compatibility.

Innovation Solution

A method involving image segmentation, digital human selection based on aesthetic compatibility, and clothing texture generation using large models to create personalized digital humans that resonate with target objects, combined with driving parameters for human-like interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If existing technologies are used to personify target objects in digital humans, then digital human generation is achieved, but feature matching between different species and aesthetic compatibility are poor

Engineering Contradiction:
Improvefeature matching precisionVSAvoidcross-species adaptability
Core Design Contradiction:
Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

The patent introduces a clothing texture as an intermediary element between the target object and the digital human. The clothing texture serves as a mediator that carries appearance features from the target object (such as pets) and transfers them to the digital human, enabling cross-species feature matching without directly merging different species' characteristics. This intermediary approach maintains aesthetic compatibility while achieving the desired personification effect.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If digital human generation is simplified, then generation speed is improved, but personalization and emotional engagement are reduced

Engineering Contradiction:
Improvegeneration speedVSAvoidpersonalization capability
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent employs preliminary action by pre-generating a diverse digital human set with various appearances, expressions, and characteristics before the actual generation process. When a target object needs to be personified, the system selects from this pre-prepared set and applies the clothing texture with extracted appearance features. This approach maintains high generation speed while achieving strong personalization, as the bulk of the creative work is done in advance and only minor adjustments are needed for each specific target object.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20260080889A1Method for generating digital human, intelligent agent, electronic device and storage medium
Publication Date: 2026.03.19 BEIJING BAIDU NETCOM SCI & TECH CO LTD
  • US20260080889A1 patent drawing
  • US20260080889A1 patent drawing
  • US20260080889A1 patent drawing

AI summary

Provided is a method for generating a digital human, an intelligent agent, an electronic device and a storage medium, relating to the field of artificial intelligence technology, and particularly to the fields of computer vision, deep learning, large model, augmented reality and other technologies. The method includes: segmenting a target object from an image to be processed to obtain a target sub-image; selecting a digital human to be optimized that is compatible with the target object from a digital human set based on the target sub-image; generating clothing texture of the digital human to be optimized based on an appearance feature of the target object in the target sub-image; applying the clothing texture to the digital human to be optimized to obtain a target digital human; and driving the target digital human.