Fine-Grained 3D Facial Reconstruction for Micro-Expressions
This work tackles the problem of accurately reconstructing subtle micro-expressions in 3D, which is crucial for applications in psychology, security, and human-computer interaction, representing an incremental advancement in facial reconstruction.
This paper addresses the unexplored challenge of 3D facial reconstruction for micro-expressions, which are subtle and low-intensity. The authors propose a method that combines global dynamic features with locally-enriched features, achieving superior performance over state-of-the-art methods in both geometric accuracy and perceptual detail on micro-expression datasets.
Recent advances in 3D facial expression reconstruction have demonstrated remarkable performance in capturing macro-expressions, yet the reconstruction of micro-expressions remains unexplored. This novel task is particularly challenging due to the subtle, transient, and low-intensity nature of micro-expressions, which complicate the extraction of stable and discriminative features essential for accurate reconstruction. In this paper, we propose a fine-grained micro-expression reconstruction method that integrates a global dynamic feature capturing stable facial motion patterns with a locally-enriched feature incorporating multiple informative cues from 2D motions, facial priors and 3D facial geometry. Specifically, we devise a plug-and-play dynamic-encoded module to extract micro-expression feature for global facial action, allowing it to leverage prior knowledge from abundant macro-expression data to mitigate the scarcity of micro-expression data. Subsequently, a dynamic-guided mesh deformation module is designed for extracting aggregated local features from dense optical flow, sparse landmark cues and facial mesh geometry, which adaptively refines fine-grained facial micro-expression without compromising global 3D geometry. Extensive experiments on micro-expression datasets demonstrate that our method consistently outperforms state-of-the-art methods in both geometric accuracy and perceptual detail.