Neural Shape Deformation Priors

We present Neural Shape Deformation Priors, a novel method for shape manipulation that predicts mesh deformations of non-rigid objects from user-provided handle movements. State-of-the-art methods cast this problem as an optimization task, where the input source mesh is iteratively deformed to minimize an objective function according to hand-crafted regularizers such as ARAP. In this work, we learn the deformation behavior based on the underlying geometric properties of a shape, while leveraging a large-scale dataset containing a diverse set of non-rigid deformations. Specifically, given a source mesh and desired target locations of handles that describe the partial surface deformation, we predict a continuous deformation field that is defined in 3D space to describe the space deformation. To this end, we introduce transformer-based deformation networks that represent a shape deformation as a composition of local surface deformations. It learns a set of local latent codes anchored in 3D space, from which we can learn a set of continuous deformation functions for local surfaces. Our method can be applied to challenging deformations and generalizes well to unseen deformations. We validate our approach in experiments using the DeformingThing4D dataset, and compare to both classic optimization-based and recent neural network-based methods.

Cross-Subject Domain Adaptation for Multi-Frame EEG Images

Working memory (WM) is a basic part of human cognition, which plays an important role in the study of human cognitive load. Among various brain imaging techniques, electroencephalography has shown its advantage on easy access and reliability. However, one of the critical challenges is that individual difference may cause the ineffective results, especially when the established model meets an unfamiliar subject. In this work, we propose a cross-subject deep adaptation model with spatial attention (CS-DASA) to generalize the workload classifications across subjects. First, we transform time-series EEG data into multi-frame EEG images incorporating more spatio-temporal information. First, the subject-shared module in CS-DASA receives multi-frame EEG image data from both source and target subjects and learns the common feature representations. Then, in subject-specific module, the maximum mean discrepancy is implemented to measure the domain distribution divergence in a reproducing kernel Hilbert space, which can add an effective penalty loss for domain adaptation. Additionally, the subject-to-subject spatial attention mechanism is employed to focus on the most discriminative spatial feature in EEG image data. Experiments conducted on a public WM EEG dataset containing 13 subjects show that the proposed model is capable of achieve better performance than existing state-of-the art methods.