Predicting natural and diverse 3D hand gestures from the upper body dynamics is a practical yet challenging task in virtual avatar creation. Previous works usually overlook the asymmetric motions between two hands and generate two hands in a holistic manner, leading to unnatural results. In this work, we introduce a novel bilateral hand disentanglement based two-stage 3D hand generation method to achieve natural and diverse 3D hand prediction from body dynamics. In the first stage, we intend to generate natural hand gestures by two hand-disentanglement branches. Considering the asymmetric gestures and motions of two hands, we introduce a Spatial-Residual Memory (SRM) module to model spatial interaction between the body and each hand by residual learning. To enhance the coordination of two hand motions wrt. body dynamics holistically, we then present a Temporal-Motion Memory (TMM) module. TMM can effectively model the temporal association between body dynamics and two hand motions. The second stage is built upon the insight that 3D hand predictions should be non-deterministic given the sequential body postures. Thus, we further diversify our 3D hand predictions based on the initial output from the stage one. Concretely, we propose a Prototypical-Memory Sampling Strategy (PSS) to generate the non-deterministic hand gestures by gradient-based Markov Chain Monte Carlo (MCMC) sampling. Extensive experiments demonstrate that our method outperforms the state-of-the-art models on the B2H dataset and our newly collected TED Hands dataset. The dataset and code are available at https://github.com/XingqunQi-lab/Diverse-3D-Hand-Gesture-Prediction.
With the inspiration of vision transformers, the concept of depth-wise convolution revisits to provide a large Effective Receptive Field (ERF) using Large Kernel (LK) sizes for medical image segmentation. However, the segmentation performance might be saturated and even degraded as the kernel sizes scaled up (e.g., $21\times 21\times 21$) in a Convolutional Neural Network (CNN). We hypothesize that convolution with LK sizes is limited to maintain an optimal convergence for locality learning. While Structural Re-parameterization (SR) enhances the local convergence with small kernels in parallel, optimal small kernel branches may hinder the computational efficiency for training. In this work, we propose RepUX-Net, a pure CNN architecture with a simple large kernel block design, which competes favorably with current network state-of-the-art (SOTA) (e.g., 3D UX-Net, SwinUNETR) using 6 challenging public datasets. We derive an equivalency between kernel re-parameterization and the branch-wise variation in kernel convergence. Inspired by the spatial frequency in the human visual system, we extend to vary the kernel convergence into element-wise setting and model the spatial frequency as a Bayesian prior to re-parameterize convolutional weights during training. Specifically, a reciprocal function is leveraged to estimate a frequency-weighted value, which rescales the corresponding kernel element for stochastic gradient descent. From the experimental results, RepUX-Net consistently outperforms 3D SOTA benchmarks with internal validation (FLARE: 0.929 to 0.944), external validation (MSD: 0.901 to 0.932, KiTS: 0.815 to 0.847, LiTS: 0.933 to 0.949, TCIA: 0.736 to 0.779) and transfer learning (AMOS: 0.880 to 0.911) scenarios in Dice Score.
In this work, we propose a new Dual Min-Max Games (DMMG) based self-supervised skeleton action recognition method by augmenting unlabeled data in a contrastive learning framework. Our DMMG consists of a viewpoint variation min-max game and an edge perturbation min-max game. These two min-max games adopt an adversarial paradigm to perform data augmentation on the skeleton sequences and graph-structured body joints, respectively. Our viewpoint variation min-max game focuses on constructing various hard contrastive pairs by generating skeleton sequences from various viewpoints. These hard contrastive pairs help our model learn representative action features, thus facilitating model transfer to downstream tasks. Moreover, our edge perturbation min-max game specializes in building diverse hard contrastive samples through perturbing connectivity strength among graph-based body joints. The connectivity-strength varying contrastive pairs enable the model to capture minimal sufficient information of different actions, such as representative gestures for an action while preventing the model from overfitting. By fully exploiting the proposed DMMG, we can generate sufficient challenging contrastive pairs and thus achieve discriminative action feature representations from unlabeled skeleton data in a self-supervised manner. Extensive experiments demonstrate that our method achieves superior results under various evaluation protocols on widely-used NTU-RGB+D and NTU120-RGB+D datasets.
Cooperative multi-agent reinforcement learning (c-MARL) offers a general paradigm for a group of agents to achieve a shared goal by taking individual decisions, yet is found to be vulnerable to adversarial attacks. Though harmful, adversarial attacks also play a critical role in evaluating the robustness and finding blind spots of c-MARL algorithms. However, existing attacks are not sufficiently strong and practical, which is mainly due to the ignorance of complex influence between agents and cooperative nature of victims in c-MARL. In this paper, we propose adversarial minority influence (AMI), the first practical attack against c-MARL by introducing an adversarial agent. AMI addresses the aforementioned problems by unilaterally influencing other cooperative victims to a targeted worst-case cooperation. Technically, to maximally deviate victim policy under complex agent-wise influence, our unilateral attack characterize and maximize the influence from adversary to victims. This is done by adapting a unilateral agent-wise relation metric derived from mutual information, which filters out the detrimental influence from victims to adversary. To fool victims into a jointly worst-case failure, our targeted attack influence victims to a long-term, cooperatively worst case by distracting each victim to a specific target. Such target is learned by a reinforcement learning agent in a trial-and-error process. Extensive experiments in simulation environments, including discrete control (SMAC), continuous control (MAMujoco) and real-world robot swarm control demonstrate the superiority of our AMI approach. Our codes are available in https://anonymous.4open.science/r/AMI.
To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. Our empirical study, however, suggests that mainstream uncertainty-based and diversity-based active learning policies are not effective when applied in the 3D detection task, as they fail to balance the trade-off between point cloud informativeness and box-level annotation costs. To overcome this limitation, we jointly investigate three novel criteria in our framework Crb for point cloud acquisition - label conciseness}, feature representativeness and geometric balance, which hierarchically filters out the point clouds of redundant 3D bounding box labels, latent features and geometric characteristics (e.g., point cloud density) from the unlabeled sample pool and greedily selects informative ones with fewer objects to annotate. Our theoretical analysis demonstrates that the proposed criteria align the marginal distributions of the selected subset and the prior distributions of the unseen test set, and minimizes the upper bound of the generalization error. To validate the effectiveness and applicability of \textsc{Crb}, we conduct extensive experiments on the two benchmark 3D object detection datasets of KITTI and Waymo and examine both one-stage (\textit{i.e.}, \textsc{Second}) and two-stage 3D detectors (i.e., Pv-rcnn). Experiments evidence that the proposed approach outperforms existing active learning strategies and achieves fully supervised performance requiring $1\%$ and $8\%$ annotations of bounding boxes and point clouds, respectively. Source code: https://github.com/Luoyadan/CRB-active-3Ddet.
One surprising trait of neural networks is the extent to which their connections can be pruned with little to no effect on accuracy. But when we cross a critical level of parameter sparsity, pruning any further leads to a sudden drop in accuracy. This drop plausibly reflects a loss in model complexity, which we aim to avoid. In this work, we explore how sparsity also affects the geometry of the linear regions defined by a neural network, and consequently reduces the expected maximum number of linear regions based on the architecture. We observe that pruning affects accuracy similarly to how sparsity affects the number of linear regions and our proposed bound for the maximum number. Conversely, we find out that selecting the sparsity across layers to maximize our bound very often improves accuracy in comparison to pruning as much with the same sparsity in all layers, thereby providing us guidance on where to prune.
Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://github.com/FuxiVirtualHuman/styletalk.
Generative adversarial networks (GANs) have made great success in image inpainting yet still have difficulties tackling large missing regions. In contrast, iterative algorithms, such as autoregressive and denoising diffusion models, have to be deployed with massive computing resources for decent effect. To overcome the respective limitations, we present a novel spatial diffusion model (SDM) that uses a few iterations to gradually deliver informative pixels to the entire image, largely enhancing the inference efficiency. Also, thanks to the proposed decoupled probabilistic modeling and spatial diffusion scheme, our method achieves high-quality large-hole completion. On multiple benchmarks, we achieve new state-of-the-art performance. Code is released at https://github.com/fenglinglwb/SDM.
In this work, we propose a semantic flow-guided two-stage framework for shape-aware face swapping, namely FlowFace. Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our FlowFace can transfer both of them to a target face, thus leading to more realistic face swapping. Concretely, our FlowFace consists of a face reshaping network and a face swapping network. The face reshaping network addresses the shape outline differences between the source and target faces. It first estimates a semantic flow (i.e., face shape differences) between the source and the target face, and then explicitly warps the target face shape with the estimated semantic flow. After reshaping, the face swapping network generates inner facial features that exhibit the identity of the source face. We employ a pre-trained face masked autoencoder (MAE) to extract facial features from both the source face and the target face. In contrast to previous methods that use identity embedding to preserve identity information, the features extracted by our encoder can better capture facial appearances and identity information. Then, we develop a cross-attention fusion module to adaptively fuse inner facial features from the source face with the target facial attributes, thus leading to better identity preservation. Extensive quantitative and qualitative experiments on in-the-wild faces demonstrate that our FlowFace outperforms the state-of-the-art significantly.