Qingsong Yan

Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training

Yixiong Yang, Sisheng Zhang, Qingsong Yan, Shaohuai Shi et autres

A key bottleneck in 3D Gaussian Splatting training is the continual growth of Gaussian primitives, which increases optimization cost and slows convergence, especially at high resolutions. We propose Laplacian Frequency Hierarchies, a simple yet efficient 3DGS scheme that combines Laplacian image decomposition …

Microstructure Evolution of Silica Sol Shell Layers Regulated by Polyethylene Powder and Its Influence on Permeability

Gang Lu, Jinglei Chen, Qingsong Yan, Yong Li

cn (code pays fourni par la source)

Regulatory mechanism of solid-liquid interface evolution on the microstructure and high-temperature properties of mullite-corundum ceramic shells

Jinglei Chen, Qingsong Yan, Jinliang Li, Wenhui Xu

cn (code pays fourni par la source)

2DGS-R: Revisiting the Normal Consistency Regularization in 2D Gaussian Splatting

Haofan Ren, Qingsong Yan, Ming‐De Lu, Rongfeng Lu et autres

Recent advancements in 3D Gaussian Splatting (3DGS) have greatly influenced neural fields, as it enables high-fidelity rendering with impressive visual quality. However, 3DGS has difficulty accurately representing surfaces. In contrast, 2DGS transforms the 3D volume into a collection of 2D planar Gaussian …

RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories

Qingsong Yan, Qiang Wang, Kaiyong Zhao, Jie Chen et autres

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to address this issue by introducing external constraints but …

cn, us, hk, gb (code pays fourni par la source)

3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene

Shihan Chen, Zhaojin Li, Zeyu Chen, Qingsong Yan et autres

Recent developments in 3D Gaussian Splatting have made significant advances in surface reconstruction. However, scaling these methods to large-scale scenes remains challenging due to high computational demands and the complex dynamic appearances typical of outdoor environments. These challenges hinder the application in …

hk, cn (code pays fourni par la source)

Wonder3D++: Cross-Domain Diffusion for High-Fidelity 3D Generation From a Single Image

Xiaoxiao Long, Zhiyang Dou, Cheng Lin, Yuan Liu et autres

In this work, we introduce Wonder3D++, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer …

cn, hk, mo, us (code pays fourni par la source)

MeshSegNet: a local to global feature fusion-based semantic segmentation approach for urban meshes

Qingsong Yan, Teng Xiao, Fei Deng

Mesh semantic segmentation is essential for 3D scene understanding, with applications in urban planning, autonomous navigation, and smart city. However, the irregular structure of meshes limits the extraction of global information, and the noise also poses a challenge to high-precision semantic segmentation …

cn, de (code pays fourni par la source)

A Deep Single Image Rectification Approach for Pan-Tilt-Zoom Cameras

Teng Xiao, Qi Hu, Qingsong Yan, Wei Liu et autres

Pan-Tilt-Zoom (PTZ) cameras with wide-angle lenses are widely used in surveillance but often require image rectification due to their inherent nonlinear distortions. Current deep learning approaches typically struggle to maintain fine-grained geometric details, resulting in inaccurate rectification. This paper presents a Forward …

cn (code pays fourni par la source)

Zero-shrinkage densification of Y2O3-based ceramic cores via in-situ Al reaction and sintering temperature control

Gang Lu, Jinglei Chen, Qingsong Yan, Zhixin Tu et autres

cn (code pays fourni par la source)

3D Gaussian Splatting for Fine-Detailed Surface Reconstruction in Large-Scale Scene

Shihan Chen, Zhaojin Li, Zeyu Chen, Qingsong Yan et autres

Recent developments in 3D Gaussian Splatting have made significant advances in surface reconstruction. However, scaling these methods to large-scale scenes remains challenging due to high computational demands and the complex dynamic appearances typical of outdoor environments. These challenges hinder the application in …

RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories

Qingsong Yan, Qiang Wang, Kaiyong Zhao, Jie Chen et autres

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to address this issue by introducing external constraints but …