3D Oral Cavity Registration for Realistic Facial Expression Models

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional face synthesis technologies often result in distorted and unrealistic oral cavity representations due to inconsistencies in size, brightness, and opening/closing forms, leading to poor synthesis effects.

Innovation Solution

A method involving obtaining a three-dimensional face model, selecting a sample oral cavity model, registering it using position parameters, adjusting its form and brightness to match the face model, and generating a three-dimensional face expression model by integrating the adjusted oral cavity model with the face model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If a 3D oral cavity model is directly fused into the 3D face model, then the oral cavity can be synthesized in three dimensions, but the size, brightness, and opening/closing form of the oral cavity model are difficult to keep consistent with the face model, resulting in poor synthesis effect

Engineering Contradiction:
Improveconsistency of size, brightness, and form between oral cavity model and face modelVSAvoidcomplexity of oral cavity synthesis process
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-adjusting the oral cavity model's size, brightness, and form parameters before fusion with the face model. The system performs form adjustment on the oral cavity model based on the expression parameter of the face model, and adjusts brightness based on skin color brightness, ensuring consistency before the actual synthesis operation occurs.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements parameter changes by modifying multiple parameters of the oral cavity model including size parameters (scaling), brightness parameters (based on skin color brightness), and form parameters (opening/closing form based on expression parameter). These parameter adjustments ensure the oral cavity model consistently matches the face model across different expressions and lighting conditions.

Inventive Principle:
Principle #35Parameter changes

2Ease of manufacture

If an oral cavity 2D picture is selected from a database based on skin color, then the selection process is simple, but it cannot be ensured that the oral cavity picture is completely consistent with the oral cavity form in the original picture, resulting in poor fusion effect

Engineering Contradiction:
Improveease of oral cavity picture selectionVSAvoidconsistency between selected oral cavity picture and original picture
Core Design Contradiction:
Ease of manufactureVSManufacturing precision

Solution Approach 1:

The patent applies parameter changes by adjusting the oral cavity model's form parameter based on the expression parameter detected from the original picture. This ensures that the synthesized oral cavity matches the specific expression (opening/closing form) in the original image, going beyond simple skin color matching to achieve form consistency as well.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If only expression transfer is carried out without modifying teeth and other oral details, then the processing is simple, but the visual effect of the obtained image is very abrupt and strange

Engineering Contradiction:
Improveprocessing speedVSAvoidrealism of synthesis effect
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The patent applies preliminary action by performing form adjustment and brightness adjustment on the oral cavity model before fusion with the face model. This preliminary processing ensures that the oral cavity details (teeth, tongue, etc.) are properly adjusted to match the face model's expression and lighting, avoiding abrupt visual effects while maintaining efficient processing.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3783571B1Three-dimensional face modeling including oral cavity
Publication Date: 2025.11.26 TENCENT TECHNOLOGY (SHENZHEN) CO LTD
  • EP3783571B1 patent drawingFigure 1a
  • EP3783571B1 patent drawingFigure 1b
  • EP3783571B1 patent drawingFigure 2~3

AI summary

Disclosed by the embodiments of the present invention are a face model processing method and device, a nonvolatile computer-readable storage medium and an electronic device, the method comprising the following steps: acquiring a three-dimensional face model corresponding to a user picture, and acquiring a selected sample oral cavity model from an oral cavity model library; registering the sample oral cavity model into the three-dimensional face model using an oral cavity position parameter in the three-dimensional face model; adjusting the oral cavity morphology of the registered sample oral cavity model by using an expression parameter of the three-dimensional face model so as to generate a target oral cavity model; and generating a three-dimensional facial expression model corresponding to the user picture on the basis of the three-dimensional face model and the target oral cavity model.