Parameter Efficient Local Implicit Image Function Network for Face Segmentation
This enables facial segmentation on low-compute or low-bandwidth devices due to higher FPS and smaller model size, but it is incremental as it builds on existing implicit function networks.
The authors tackled face parsing by proposing FP-LIIF, a lightweight method using a Local Implicit Function network, which matches or outperforms state-of-the-art models on datasets like CelebAMask-HQ and LaPa while using 1/26th the parameters and enabling segmentation at different resolutions without input changes.
Face parsing is defined as the per-pixel labeling of images containing human faces. The labels are defined to identify key facial regions like eyes, lips, nose, hair, etc. In this work, we make use of the structural consistency of the human face to propose a lightweight face-parsing method using a Local Implicit Function network, FP-LIIF. We propose a simple architecture having a convolutional encoder and a pixel MLP decoder that uses 1/26th number of parameters compared to the state-of-the-art models and yet matches or outperforms state-of-the-art models on multiple datasets, like CelebAMask-HQ and LaPa. We do not use any pretraining, and compared to other works, our network can also generate segmentation at different resolutions without any changes in the input resolution. This work enables the use of facial segmentation on low-compute or low-bandwidth devices because of its higher FPS and smaller model size.