Style-Aware Puppets for Animation Texture Consistency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional computer-animation systems face limitations in accurately replicating the motion and artistic style of hand-drawn characters in computerized animation sequences, often resulting in inconsistent or unnatural textures and restricted motion ranges, which can lead to stiff or jerky animations.

Innovation Solution

The use of style-aware puppets, comprising a character-deformation model, skeletal-difference map, and visual-texture representation, allows for the preservation and transfer of detailed visual appearance and stylized motion from a source-character-animation sequence to a target-character-animation sequence, enabling more flexible and accurate rendering of motion and texture.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional computer-animation systems compress or stretch a visual texture of an animation character from frame to frame to create animation sequences, then the animation character can be reused across frames, but the visual texture becomes inconsistent or contorted

Engineering Contradiction:

Improveanimation sequence generation efficiencyVSAvoidvisual texture consistency

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The system segments the animation character into a skeletal structure and a visual texture layer. The skeletal structure handles the motion and deformation, while the visual texture layer remains separate and is applied to the deformed skeleton. This segmentation allows the texture to be reused without being compressed or stretched, maintaining consistency while enabling efficient animation sequence generation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces a skeletal structure as an intermediary between the rigid visual texture and the desired animated motion. The skeleton acts as a mediator that can deform and move freely while the visual texture is applied to its surface, preventing direct distortion of the texture while still achieving natural-looking animation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Manufacturing precision

If conventional computer-animation systems impose rigid limits on an animation character's visual texture to avoid textural inconsistencies, then the visual texture remains fixed and consistent, but the animation character appears unnatural and un-animated

Engineering Contradiction:

Improvevisual texture consistencyVSAvoidanimation naturalness

Core Design Contradiction:

Manufacturing precisionVSEase of operation

Solution Approach 1:

By separating the visual texture from the skeletal structure, the system allows the texture to remain consistent and fixed while the skeleton provides natural, animated deformation. This segmentation resolves the contradiction by enabling the texture to be rigid (for consistency) while the overall character appearance remains natural through skeletal deformation.

Inventive Principle:

Principle #1Segmentation

3Device complexity

If conventional computer-animation systems provide a limited set of transformations for an animation character layer, then the animation process is simplified, but the system cannot generate bulging, exaggerated bending, or secondary effects

Engineering Contradiction:

Improvetransformation set sizeVSAvoidmotion expression capability

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system replaces static, limited transformation sets with a dynamic skeletal structure that can compute any necessary deformation. The skeleton can be dynamically deformed to create bulging, exaggerated bending, and secondary effects by adjusting joint positions and rotations, providing unlimited motion expression capability without increasing the complexity of the transformation math itself.

Inventive Principle:

Principle #15Dynamics

4Ease of manufacture

If computer-animation systems use a single-drawing-based approach to create animation sequences, then the production process is simplified, but the system cannot accurately replicate the motion and artistic style of hand-drawn characters

Engineering Contradiction:

Improveproduction process simplicityVSAvoidmotion and style replication accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system creates a skeletal structure that copies the motion trajectory and deformation patterns from hand-drawn reference animations. By capturing the essential motion data from the reference and applying it through the skeleton, the system achieves accurate replication of both motion and artistic style while maintaining a simplified single-drawing-based production process.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS10789754B2Generating target-character-animation sequences based on style-aware puppets patterned after source-character-animation sequences

Publication Date: 2020.09.29 ADOBE INC

AI summary

This disclosure relates to methods, non-transitory computer readable media, and systems that use style-aware puppets patterned after a source-character-animation sequence to generate a target-character-animation sequence. In particular, the disclosed systems can generate style-aware puppets based on an animation character drawn or otherwise created (e.g., by an artist) for the source-character-animation sequence. The style-aware puppets can include, for instance, a character-deformational model, a skeletal-difference map, and a visual-texture representation of an animation character from a source-character-animation sequence. By using style-aware puppets, the disclosed systems can both preserve and transfer a detailed visual appearance and stylized motion of an animation character from a source-character-animation sequence to a target-character-animation sequence.