Recently, neural networks have shown promising results in human pose estimation. However, existing datasets typically cover only a limited range of viewpoints and lack sufficient diversity in environments, which significantly restricts the further improvement of estimation performance. To address this issue, we propose a novel three-stage synthetic data augmentation method that incorporates 3DGS-based novel view synthesis, known for its photo-realistic capabilities. In the 3D synthesis stage, we develop a HumanEnv Builder to create diverse combinations of human and environments. In the novel view generation stage, we introduce a naturally designed camera extrinsics planner to simulate realistic shooting conditions. In the label generation stage, we present an intrinsic label transformer to derive pose-related ground truth. Experimental results demonstrate that NVPose, our novel view data augmentation method, significantly enhances the performance of four human pose estimation models across diverse datasets and achieves state-of-the-art results compared to existing data augmentation methods.

Moving object segmentation plays a vital role in understanding dynamic visual environments. While existing methods rely on multi-frame image sequences to identify moving objects, single-image MOS is critical for applications like motion intention prediction and handling camera frame drops. However, segmenting moving objects from a single image remains challenging for existing methods due to the absence of temporal cues. To address this gap, we propose MovSAM, the first framework for single-image moving object segmentation. MovSAM leverages a Multimodal Large Language Model (MLLM) enhanced with Chain-of-Thought (CoT) prompting to search the moving object and generate text prompts based on deep thinking for segmentation. These prompts are cross-fused with visual features from the Segment Anything Model (SAM) and a Vision-Language Model (VLM), enabling logic-driven moving object segmentation. The segmentation results then undergo a deep thinking refinement loop, allowing MovSAM to iteratively improve its understanding of the scene context and inter-object relationships with logical reasoning. This innovative approach enables MovSAM to segment moving objects in single images by considering scene understanding. We implement MovSAM in the real world to validate its practical application and effectiveness for autonomous driving scenarios where the multi-frame methods fail. Furthermore, despite the inherent advantage of multi-frame methods in utilizing temporal information, MovSAM achieves state-of-the-art performance across public MOS benchmarks, reaching 92.5% on J&F. Our implementation will be available at https://github.com/IRMVLab/MovSAM.

Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents Receding Horizon Inverse Reinforcement Learning (RHIRL), a new IRL algorithm for high-dimensional, noisy, continuous systems with black-box dynamic models. RHIRL addresses two key challenges of IRL: scalability and robustness. To handle high-dimensional continuous systems, RHIRL matches the induced optimal trajectories with expert demonstrations locally in a receding horizon manner and stitches'' together the local solutions to learn the cost; it thereby avoids thecurse of dimensionality''. This contrasts sharply with earlier algorithms that match with expert demonstrations globally over the entire high-dimensional state space. To be robust against imperfect expert demonstrations and control noise, RHIRL learns a state-dependent cost function ``disentangled'' from system dynamics under mild conditions. Experiments on benchmark tasks show that RHIRL outperforms several leading IRL algorithms in most instances. We also prove that the cumulative error of RHIRL grows linearly with the task duration.

A weighted densely connected convolution network (W-DenseNet) is proposed for reinforcement learning in this work. The W-DenseNet can maximize the information flow between all layers in the network by cross layer connection, which can reduce the phenomenon of gradient vanishing and degradation, and greatly improves the speed of training convergence. The weight coefficient introduced in W-DenseNet, the current layer received all the previous layers’ feature maps with different initial weights, which can extract feature information of different layers more effectively according to tasks. According to the weight adjusted by learning, the cross-layer connection is pruned to remove the cross-layer connection with smaller weight, so as to reduce the number of cross-layer. In this work, GridWorld and FlappyBird games are used for simulation. The simulation results of deep reinforcement learning based on W-DenseNet are compared with the traditional deep reinforcement learning algorithm and reinforcement learning algorithm based on DenseNet. The simulation results show that the proposed W-DenseNet method can make the results more convergent, reduce the training time, and obtain more stable results.

The biometric information contained in a face image is affected by many factors such as living environment, racial differences, and genetic diversity, this complexity leads to the nonstationary of the age estimation. In order to reduce the overlap of face features between adjacent ages and improve the accuracy of age prediction, a multi-stage feature constraints learning method is proposed for face age estimation. The proposed method gradually refines the feature through three feature constraint stages. In each stage, the algorithm continuously updates the feature center of its corresponding age range, and minimizes the distance between each age feature and feature center of the corresponding age range through feature constraint. Feature constraint makes the feature distances between different individuals in the same age feature space smaller and decrease the overlap areas between adjacent age range feature spaces. Meanwhile, the feature distance of different age range feature space is enlarged. The proposed network efficiently merges the features of three stages and optimizes the mapping of feature maps to an ordered binary comparison space. Experiments show that the proposed method is able to effectively improve the discrimination between different age features, and hence to improve the accuracy of face age estimation. In addition, the proposed algorithm is simple enough to achieve fast face age estimation.