Shadow Generation for Embedded Objects Using Mask Categorization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image editing technologies face challenges in generating natural-looking shadows for objects embedded in target images, especially when the light source is unclear or multiple, as precise determination of light source location is required, leading to unnatural appearances of embedded objects.
Innovation Solution
An apparatus and method for shadow generation categorize objects into 'sitting' or 'standing' categories based on object mask characteristics, using dilation for sitting objects and depth information for standing objects, with shadows generated based on ambient light sources, including multiple point light sources positioned in a circular pattern.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If precise determination of light source location is used to generate shadows, then shadow accuracy is improved, but device complexity and operation difficulty increase
Solution Approach 1:
The system automatically determines object categories (sitting/standing) and generates shadows using ambient light sources without requiring manual light source location input. The object mask itself serves as the basis for shadow generation, eliminating the need for separate light source analysis.
Solution Approach 2:
The system changes the approach from precise light source location determination to using predefined ambient light source positions. By categorizing objects and applying different shadow generation methods based on category rather than calculating exact light source positions, the system simplifies the measurement requirements.
2Productivity
If automated shadow generation is implemented, then productivity is improved, but shadow quality may deteriorate
Solution Approach 1:
The system segments objects into two categories (sitting and standing) and applies different shadow generation methods to each category. This segmentation allows for optimized automated processing while maintaining quality, as each category can be handled with the most appropriate algorithm.
Solution Approach 2:
The system uses object masks as templates to generate shadows. By copying the spatial information from the object mask and applying it to predefined light source positions, the system achieves both automation and quality preservation.
3Reliability
If multiple light sources are considered, then shadow realism is improved, but measurement precision requirements increase
Solution Approach 1:
The system handles multiple light source scenarios universally by using predefined ambient light source positions that work for various lighting conditions. Instead of requiring precise measurement of actual light sources, the system applies a universal approach that accommodates different lighting setups.
Data Source
AI summary
Various aspects of an apparatus and a method to generate a shadow of an object embedded in a target image are disclosed herein. The method includes generation of an object mask of the embedded object in the target image. The object mask is categorized into a first category or a second category based on a pre-determined set of rules. Based on the categorization, a shadow of the object in the target image is generated. The generation of the shadow comprises dilating the categorized object mask by a predetermined multiplication factor when the categorized object mask corresponds to the first category. The generation of the shadow further comprises determination of depth information of the categorized object mask at a pre-determined height when the categorized object mask corresponds to the second category.