High-fidelity 3D face reconstruction with multi-scale details

•We propose a novel cascaded framework to reconstruct 3D faces with subtle details.•By detaching details from the texture, we enhance the recovered geometry details.•We design a staged strategy to capture details over multiple scales. Despite tremendous success has been achieved in faithfully reconstructing face shapes from single images, recovering accurate local details still remains challenging. Previous works propose reprojection-based methods to improve the performance of detail recovering – they render a textured 3D shape into an image and make it approximate to the input during iterations. However, details from textures and shapes are mixed in the rendered image when minimizing the re-projection loss, which leads to limitations in detail recovery. To address this issue, we propose a novel 3D face reconstruction framework that 1) uses a coarse-medium-fine strategy to capture details while preserving the global shape, 2) disentangles details from the texture to enhance local accuracy, and 3) applies a phased optimization to recover details over multiple scales. Experiments demonstrate the capability of our framework to reconstruct high-fidelity face shapes with accurate, fine details.