OFER: Occluded Face Expression Reconstruction

4 Microsoft Research, Redmond (c) Best Ranked Neutral shape (b) Worst ranked Neutral shape (a) Input Image (d) Expression recontructions using (c) Figure 1. Reconstructions generated by OFER. Our method can reconstruct faces from a single image under hard occlusions (a), providing multiple solutions with diverse expressions that align with the input image (d). We use two diffusion models that denoise the shape and expression parameters of FLAME conditioned on the image. A novel ranking mechanism selects an optimal identity (c) from the generated set of shapes, on top of which the expression variants are applied to obtain the final results.