Revisiting an Old Perspective Projection for Monocular 3D Morphable Models Regression
This work addresses the limitation of existing 3DMM regression methods for content creators working with close-up facial footage from devices like head-mounted cameras, by improving their ability to handle perspective distortion.
This paper introduces a new camera model for monocular 3D Morphable Model (3DMM) regression, designed to handle perspective distortion in close-up facial images. By extending orthographic projection with a shrinkage parameter, the method effectively incorporates a pseudo-perspective effect while maintaining stability, as demonstrated on a custom dataset.
We introduce a novel camera model for monocular 3D Morphable Model (3DMM) regression methods that effectively captures the perspective distortion effect commonly seen in close-up facial images. Fitting 3D morphable models to video is a key technique in content creation. In particular, regression-based approaches have produced fast and accurate results by matching the rendered output of the morphable model to the target image. These methods typically achieve stable performance with orthographic projection, which eliminates the ambiguity between focal length and object distance. However, this simplification makes them unsuitable for close-up footage, such as that captured with head-mounted cameras. We extend orthographic projection with a new shrinkage parameter, incorporating a pseudo-perspective effect while preserving the stability of the original projection. We present several techniques that allow finetuning of existing models, and demonstrate the effectiveness of our modification through both quantitative and qualitative comparisons using a custom dataset recorded with head-mounted cameras.