Learning a physical model from video data that can comprehend physical laws and predict the future trajectories of objects is a formidable challenge in artificial intelligence. Prior approaches either leverage various Partial Differential Equations (PDEs) as soft constraints in the form of PINN losses, or integrate physics simulators into neural networks; however, they often rely on strong priors or high-quality geometry reconstruction. In this paper, we propose CausalGS, a framework that learns the causal dynamics of complex dynamic 3D scenes solely from multi-view videos, while dispensing with the reliance on explicit priors. At its core is an inverse physics inference module that decouples the complex dynamics problem from the video into the joint inference of two factors: the initial velocity field representing the scene’s kinematics, and the intrinsic material properties governing its dynamics. This inferred physical information is then utilized within a differentiable physics simulator to guide the learning process in a physics-regularized manner. Extensive experiments demonstrate that CausalGS surpasses the state-of-the-art on the highly challenging task of long-term future frame extrapolation, while also exhibiting advanced performance in novel view interpolation. Crucially, our work shows that, without any human annotation, the model is able to learn the complex interactions between multiple physical properties and understand the causal relationships driving the scene’s dynamic evolution, solely from visual observations. We anonymously provide the code at https://github.com/DustSettled/CausalGS.

Semi-supervised segmentation (S3) is one of the preferred choices for histopathological image segmentation tasks, while how to improve model’s learning capability for unlabeled data remains a key challenge in S3. The remarkable feature extraction abilities of Segment Anything Model (SAM) offers a potential opportunity. However, SAM’s performance on contextual complex histopathological images is not so desirable due to its limitations in finely capture structural relationships. To address this issue, we propose a novel SAM-based S3framework QuPaS, which consists of Quantum Force Field (QFF) Finetuning and Adversarial Estimation (AE). QFF covers the shortage of SAM’s limited understanding of spatial structure by simulating intermolecular forces to explore the structural topological relationships between pixel-level features. AE introduces an adversarial estimation network to align the consistency of confidence distributions between different outputs, thereby reducing the interference of incompatible semantic features on the model. Extensive experiments across three challenging histopathological segmentation scenarios have demonstrate that our QuPaS completely outperforms the state-of-the-art S3methods. Furthermore, QuPaS is able to maintain stable generalization performance on previously unseen domains. The code will be released at: https://github.com/director87/QuPaS.

Object detection is widely used in many fields, and multi-scale feature extraction is crucial for accurate detection. The Feature Pyramid Network (FPN) is a commonly adopted feature extraction approach in object detection. Nevertheless, direct fusion between top-down feature layers in FPN leads to misalignment and loss of feature information. To address these limitations, this paper proposes a novel feature pyramid network based on FPN, termed SAR-FPN, which consists of two components: the Scale Adaptive Triple-Branch Module (SATM) and the Reverse Feature Fusion Module (RFFM). Specifically, SATM enhances the performance for large objects through its triple-branch design. It selects the appropriate branch based on object scale, assigns suitable receptive fields for objects of different sizes, and performs feature alignment. The RFFM addresses the issue of poor performance in small object detection by implementing a bottom-up feature fusion pathway. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2017 datasets validated the effectiveness of SAR-FPN.

The combination of quantum secret sharing (QSS) and continuous-variable quantum key distribution (CV-QKD) has demonstrated clear advantages and has undergone significant development in recent years. However, research on the practical security of CV-QSS remains limited, particularly in the context of free-space channels, which exhibit considerable flexibility. In this paper, we study the practical security of free-space CV-QSS, innovatively propose an attack strategy that probabilistically combines two-point distribution attack (TDA) and uniform distribution attack (UDA). We also establish channel parameter models, especially a channel noise model based on local local oscillators (LLO), to further evaluate the key rate. In principle, the analysis can be extended to any number of probabilistic combinations of channel manipulation attacks. The numerical results demonstrate that the probabilistic combination attacks reduce the real key rate of CV-QSS. Moreover, it should be noted that the probabilistic combination attacks will make the deviation between the estimated key rate and the real key rate, i.e., the key rate is overestimated, which may pose a security risk.