Prediction Engine for Deforming 3D Graphics Edits

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing graphics editing tools for keyframe-based sculpting in Illustrator systems are inefficient due to repetitive and burdensome operations, as they fail to consider spatial-temporal similarities in brush strokes, leading to irrelevant or unexecutable suggested edits.

Innovation Solution

A prediction engine that accesses previous and current editing operations, identifies matching and non-matching components, and deforms the previous operations using a deformation model to suggest augmentative edits, reducing repetitive tasks and improving user interface navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing editing tools are used for keyframe-based sculpting, then artists can perform brush strokes and manipulation operations, but the repetitive nature of operations across multiple frames becomes burdensome and tedious

Engineering Contradiction:

Improveediting operation efficiencyVSAvoidtime for repetitive operations

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of prior editing operations across multiple frames to identify patterns and predict subsequent operations. By pre-computing the deformation model from historical data, the system prepares suggested operations before the artist needs to execute them, reducing the time spent on repetitive manual operations.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system provides feedback by analyzing the artist's actual executed operations and comparing them against predicted patterns. This feedback loop allows the deformation model to be continuously refined, improving the accuracy of suggested operations and reducing the burden of repetitive tasks over time.

Inventive Principle:

Principle #23Feedback

2Extent of automation

If existing editing tools suggest operations based on spatial or temporal similarity alone, then operations can be automated to some extent, but the suggested operations become irrelevant when artists deviate from previous patterns

Engineering Contradiction:

Improveautomation of suggested editsVSAvoidrelevance of suggested operations

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The system dynamically adapts its suggestions by continuously learning from the artist's actual deviations from predicted patterns. The deformation model is updated in real-time based on executed operations, allowing the automation to adjust its behavior and maintain relevance even when artists deviate from established patterns.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameters of operation prediction by incorporating both spatial similarity (brush stroke location and direction) and temporal similarity (sequence of operations across frames). This multi-parameter approach allows the system to maintain high reliability by considering multiple dimensions of operation characteristics simultaneously.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If existing editing tools fail to consider spatial-temporal similarity, then operations can be performed independently, but suggested operations cannot be executed within the editing tool's constraints

Engineering Contradiction:

Improveflexibility of brush stroke executionVSAvoidexecutability of suggested operations

Core Design Contradiction:

Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The system segments the editing operation into distinct components: spatial parameters (brush stroke position and direction on the mesh surface), temporal parameters (sequence and duration across frames), and deformation parameters (surface transformation). By analyzing each component separately and then recombining them, the system ensures that suggested operations are both flexible in their spatial execution and executable within the tool's constraints.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11282290B1Generating suggested edits for three-dimensional graphics based on deformations of prior edits

Publication Date: 2022.03.22 ADOBE INC

AI summary

Using a prediction engine, generating, based on deformations of prior editing operations performed with a graphics editing tool, suggested editing operations that augment current editing operations applied to a graphical object. The prediction engine accesses first samples defining first positions along first paths of previous editing operations applied to a mesh object in a previous frame and second samples defining second positions along second paths of executed editing operations applied in a current frame. The prediction engine identifies, from a comparison of the first samples and the second samples, a matching component set from the previous editing operations that corresponds to the executed editing operations. The prediction engine deforms the first samples toward the second samples and determines suggested editing operations that comprise a non-matching component set as modified based on the deformed first samples. The prediction engine updates an interface to provide the suggested editing operations.