Superdirective beamforming methods based on spherical harmonic expansion can achieve higher array gain compared to conventional beamforming methods when the array aperture is very small. However, in the waveguide environment, the array gain of beamforming methods based on spherical harmonic expansion may degrade significantly due to the influence of multipath effects. To address the issue, this letter proposes an improved beamforming method for compact planar acoustic vector sensor arrays to mitigate the negative impact of multipath effects on array gain. First, the form of the steering vector model in the direct arrival zone of the waveguide environment is reasonably simplified. Second, a closed-form beamformer is constructed by utilizing the information of signals' arriving directions. Subsequently, the theoretical derivation demonstrates the advantages of the proposed beamforming method in the waveguide environment. Finally, simulation analysis substantiates the rationality and feasibility of the proposed method.

Document images captured with cameras often exhibit photometric and geometric distortions. Here, we propose a novel learning-based approach for efficient joint rectification of document images. Inspired by the strong correlation between visual shadows and physical deformations, we design a shared encoder architecture to fully leverage structured document features. A cross-attention module is introduced to facilitate information exchange between deformation and coordinate domains. Our method effectively addresses both geometric and photometric distortions in an end-to-end manner, making it highly valuable for applications involving camera-captured document images.

High-quality reconstruction and rendering of 3D scenes has been a long-standing problem in CV and CG. Most previous methods rely on implicit representations, which require significant time overhead and limit practical applications. Several explicit representations were proposed to reduce time overhead later, but none of them can achieve high-quality real-time rendering. 3D Gaussian Splatting achieves outstanding rendering quality and speed, but it cannot be applied to dynamic scenes. In this paper, we propose a new dynamic representation called mixed Gaussian. Specifically, we use separate Gaussian models to represent the dynamics and statics of the scene. For the dynamic part, we introduce a new deformation field to model the motion of points and extend the dynamic gaussian to hyper space for dealing with complex topological changes in the scene. Experiments show that our approach achieves superior rendering quality and real-time rendering compared to previous methods.

The tasks of view synthesis and decoupling dynamic objects from the static environment for monocular scenes are both long-standing challenges in CV and CG. Most of the previous NeRF-based methods rely on implicit representation, which require additional supervision and training time. Later, various explicit representations like multi-planes or 3D gaussian splatting have been extended and applied to the task of novel view synthesis for dynamic scenes. They introduce an additional time dimension or a deformation field into the original representation to encode dynamics. Due to the effective explicit representations, these methods greatly reduce the time consumption, but still fail to achieve high rendering quality in some scenes, especially for some real scenes. For the latter decoupling problem, previous neural radiation field methods require frequent tuning of the relevant parameters for different scenes, which is very inconvenient for practical use. We consider above problems and propose a new representation of dynamic scenes based on tensor decomposition, which we call R4D-planes. The key to our method is remapping, which compensates for the shortcomings of the plane structure by fusing space-time information and remapping to new indexes. Furthermore, we implement a new decoupling structure, which can efficiently decouple dynamic and static scenes in a self-supervised manner. Experimental results show our method achieves better rendering quality and training efficiency in both view synthesis and decoupling tasks for monocular scenes.