Parametric Eye Model Reconstruction for Realistic Digital Faces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current facial capture technologies focus primarily on facial skin, neglecting important characteristics like the eyes, which are crucial for realistic animation, and existing eye capture methods are often time-consuming and uncomfortable for actors.
Innovation Solution
A parametric eye model is developed, comprising a deformable eyeball, iris, and vein models, allowing for the reconstruction of unique eye shapes and colors from sparse input data, such as single images or multi-view face scans, using a fitting technique that estimates model parameters for accurate representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional eye capture methods are used, then high quality eye data can be obtained, but the capture process becomes time-consuming and uncomfortable for actors
Solution Approach 1:
A parametric eye model is pre-built containing all possible eye shapes and colors within a standardized coordinate system. This preliminary preparation allows the system to reconstruct any eye by simply adjusting parameters rather than capturing complete 3D data during the actual capture process, dramatically reducing capture time while maintaining high quality
Solution Approach 2:
The eye model is represented by a small set of adjustable parameters including shape coefficients, color values, and scale factors. By changing these parameters, the system can reconstruct diverse eye appearances from sparse input data, achieving high-quality reconstruction without time-consuming complete scans
2Manufacturing precision
If traditional eye capture methods are used, then detailed eye features can be captured, but the capture setup becomes complex and uncomfortable
Solution Approach 1:
The parametric eye model serves multiple functions: it can represent any eye shape through shape coefficients, any eye color through color parameters, and accommodate different pupil sizes. This universal model eliminates the need for different capture setups for different eye types, simplifying the overall system while maintaining detailed feature capture capability
Solution Approach 2:
Instead of capturing complete 3D eye geometry, the system uses sparse input data (such as 2D images or limited scan points) to infer and copy the essential eye features into the parametric model. This copying approach reconstructs detailed eye features from minimal input, avoiding complex capture hardware
3Manufacturing precision
If facial capture technology focuses on skin, then skin quality is high, but other important characteristics like eyes are neglected
Solution Approach 1:
The face capture system is segmented into independent modules: skin capture and eye capture. The eye module uses the parametric model with its own dedicated parameters (shape coefficients, color values, pupil radius) that are optimized specifically for eye reconstruction, allowing high-quality eye capture without compromising skin capture quality
Data Source
AI summary
Systems and techniques for reconstructing one or more eyes using a parametric eye model are provided. The systems and techniques may include obtaining one or more input images that include at least one eye. The systems and techniques may further include obtaining a parametric eye model including an eyeball model and an iris model. The systems and techniques may further include determining parameters of the parametric eye model from the one or more input images. The parameters can be determined to fit the parametric eye model to the at least one eye in the one or more input images. The parameters include a control map used by the iris model to synthesize an iris of the at least one eye. The systems and techniques may further include reconstructing the at least one eye using the parametric eye model with the determined parameters.