Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors. Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). This decoupled architecture reduces data requirements and enables flexible integration of Large Language Models (LLMs) and Vision Language Models (VLMs) for zero-shot tasks such as image-to-scene generation. To maintain physical validity within complex floor plans, we explicitly model building elements ( e.g. , walls, doors, and windows) as conditional constraints. Furthermore, to address the high entropy of dense relation graphs, we introduce a sparse relation graph formulation aligned with human spatial descriptions. By encoding these sparse graphs into a compact latent space using a bidirectional Variational Autoencoder (VAE), the proposed framework provides enhanced relational controllability, allowing generated layouts to better respect functional organization. Experiments demonstrate that CasLayout achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.

This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.

We report analytical polarization coefficients for inhomogeneously refracted$P$-wave in the post-critical incident-angle region, induced at the interfaces between different types of anisotropic rocks. For theA-shale/T-sandstone interface, the phase velocity ofSV-wave in a largeT-sandstone is smaller than that of theP-wave inA-shale. For theA-shale/$O$-shale interface, the phase velocity ofSV-wave in$O$-shale is larger than that ofP-wave in$A$-shale in some directions but smaller in other directions. In both cases, critical incident-angles do not exist related to the refractedSV-wave. Applying the widely reported rock parameters, we have obtained typical results of slowness that provide a logical explanation for the long holding scientific puzzle that some vertical axis of symmetry-tilt axis of symmetry (VTI-TTI) interface systems appear to have a critical incidence angle but it is not real. We have obtained reflection and refraction coefficients, polarization coefficients, particle displacement of the induced homogeneous wave, the polarization state of the inhomogeneously refractedP-wave, and the elliptical polarization trajectories. We conclude that the polarization coefficients of the induced waves are determined only by the physical nature of the media, the geometric structure of the interface, and the incident-angle. The analytical polarization coefficients provide a base for accurate calculations of the reflection coefficients at the anisotropic-rocks interfaces that are widely used for amplitude variations with offset (AVO) analysis and inversion interpretation of seismic exploration data. The analyses reported in this article apply not only to the VTI-TTI interfaces but also to the generic TTI-TTI interfaces through Bond transformation.