Generating natural 3D human motions that are consistent with textual descriptions is a key task in text-to-motion generation. The Transformer-based text-conditional mask motion generation model relies on the multi-head attention mechanism and mask training strategy, making significant progress in generating high-quality and high-fidelity 3D human motions. However, these models only use the multi-head attention mechanism to capture the long-distance dependence of features, lacking the modeling of spatio-temporal relationship of motion sequence, which affects the coherence of the generated motion. In addition, the multi-head attention mechanism has limited ability to capture the detailed information of motions, which affects the authenticity and accuracy of generated motions. Therefore, we propose an augmented 3D generative masked motion model (AG-Mask), which significantly enhances the model’s ability to capture spatiotemporal feature and detailed feature of motion sequence, and effectively generates high-quality motions consistent with text descriptions. Specifically, we design two augmented bidirectional transformer in AG-Mask: STM-Transformer and MDR-Transformer, which are used to process the basic and detailed information of motions respectively. STM-Transformer can boost the information extraction ability of the model in the motion channel and spatial dimension. MDR-Transformer can model the spatio-temporal relationship of motions and extract rich multidimensional features. Their combined processing promotes the generation of motion sequence from coarse to fine, optimizing the quality of generated motions. Experiments on the HumanML3D and KIT-ML datasets show that AG-Mask achieves state-of-the-art performance in generating high-quality motions. In addition, AG-Mask refines the motion editing function, making it more flexible for practical applications.

Self-supervised monocular depth estimation has garnered widespread attention because it does not require hard-to-obtain depth labels during training. Many existing studies have focused on the design of depth encoders, often neglecting the potential of decoders, which results in decoders that struggle to utilize the multi-scale features extracted by the encoder fully, lack the ability to capture the features comprehensively, and also fall short in recovering local details. To address these issues, this paper proposes a lightweight self-supervised monocular depth estimation architecture called MD-Mono. MD-Mono employs a hybrid depth encoder combining Convolutional Neural Networks (CNNs) and Transformers, aiming to capture both local features and global semantic information. In the depth decoder, we propose an Adaptive Depth Focus (ADF) module and an Implicit Detail Enhancement (IDE) module. The ADF module adaptively adjusts each stage of the decoding process according to the input features, effectively integrating and utilizing multi-scale features. The IDE module implicitly maps the input to a high-dimensional, nonlinear feature space, capturing more detailed feature information for recovering local details. The synergy of these two modules enables our architecture to achieve a semantically richer and spatially more accurate representation with fewer parameters. Experimental results show that MD-Mono significantly outperforms Monodepth2 in terms of accuracy and exhibits good generalization ability on the Make3D and DrivingStereo datasets.

Abstract For 3D mesh pose transfer, the target model is obtained by transferring the pose of the reference mesh to the source mesh, where the shape and pose of the source are usually different from that of the reference. In this paper, pose transfer is considered as a deformation process of the source mesh, and we propose a 3D mesh pose transfer method based on skeletal deformation. First, we design a neural network based on the edge convolution operator to extract the skeleton of the 3D mesh and bind the rigid weights; then, we calculate the bone transformations between the two skeletons with different poses and use the diffusion equation to smooth the rigid weights; finally, the source mesh is deformed according to the bone transformations and the smooth weights to get the target mesh. Experiment results on different datasets show that the pose of the reference mesh can be effectively transferred to the source one while maintaining the shape and high‐quality geometric details of the source mesh by using our method.