Searcharxiv⌕ Search

arXiv subjects

Luo Wang

Publications and source records attributed to Luo Wang.

3 recordsLinked to original sources

Optimization Framework for Full-Skyrmionic Polarimetry

Optical skyrmionic beams hold considerable potential for applications in quantum information and weak-intensity detection. These applications require accurate measurements of full topological observables using imaging Stokes polarimetry, with measurement states optimized in advance to limit the effect of stochastic error sources. However, the optimization framework for general Stokes polarimetries is based on a linear reconstruction chain for Stokes vectors and cannot quantitatively evaluate the nonlinear reconstruction of topological observables. Here, we define full-skyrmionic polarimetry (FSP) and construct its optimization framework from the reconstruction chain for full topological observables. Based on existing polarization evaluating functions (PEF), we introduce topological evaluating functions (TEF) and develop a multi-stage FSP optimization methodology. Numerical results confirm that topological optimization can further improve the reconstruction of topological observables, even when the measurement states are already optimal for polarization. Increasing the redundant projection number also effectively suppresses the effects of all stochastic error sources, providing a low-cost methodology to improve the reconstruction of both polarization and topological observables. The FSP optimization framework can identify topologically optimal configurations for arbitrary FSP structures, providing a guideline for high-precision full-skyrmionic measurements at weak-intensity levels and potential skyrmion ellipsometry.

physics.optics↗

PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery

Panoramic imagery offers a full 360° field of view and is increasingly common in consumer devices. However, it introduces non-pinhole distortions that challenge joint pose estimation and 3D reconstruction. Existing feed-forward models, built for perspective cameras, generalize poorly to this setting. We propose PanoVGGT, a permutation-equivariant Transformer framework that jointly predicts camera poses, depth maps, and 3D point clouds from one or multiple panoramas in a single forward pass. The model incorporates spherical-aware positional embeddings and a panorama-specific three-axis SO(3) rotation augmentation, enabling effective geometric reasoning in the spherical domain. To resolve inherent global-frame ambiguity, we further introduce a stochastic anchoring strategy during training. In addition, we contribute PanoCity, a large-scale outdoor panoramic dataset with dense depth and 6-DoF pose annotations. Extensive experiments on PanoCity and standard benchmarks demonstrate that PanoVGGT achieves competitive accuracy, strong robustness, and improved cross-domain generalization. Code and dataset will be released.

cs.CV↗

AerialGo: Walking-through City View Generation from Aerial Perspectives

High-quality 3D urban reconstruction is essential for applications in urban planning, navigation, and AR/VR. However, capturing detailed ground-level data across cities is both labor-intensive and raises significant privacy concerns related to sensitive information, such as vehicle plates, faces, and other personal identifiers. To address these challenges, we propose AerialGo, a novel framework that generates realistic walking-through city views from aerial images, leveraging multi-view diffusion models to achieve scalable, photorealistic urban reconstructions without direct ground-level data collection. By conditioning ground-view synthesis on accessible aerial data, AerialGo bypasses the privacy risks inherent in ground-level imagery. To support the model training, we introduce AerialGo dataset, a large-scale dataset containing diverse aerial and ground-view images, paired with camera and depth information, designed to support generative urban reconstruction. Experiments show that AerialGo significantly enhances ground-level realism and structural coherence, providing a privacy-conscious, scalable solution for city-scale 3D modeling.

cs.CV↗