计算机科学
计算机视觉
人工智能
曲面重建
稀疏逼近
高斯过程
迭代重建
算法
计算机图形学(图像)
稀疏矩阵
高斯分布
曲面拟合
模式识别(心理学)
曲面(拓扑)
可视化
图像分割
图像处理
数据可视化
代表(政治)
高斯噪声
计算机图形学
噪音(视频)
特征提取
作者
Yibin Zhao,Jianjun Yi,Yihan Pan,Jun Nan
标识
DOI:10.1109/tvcg.2026.3727349
摘要
Gaussian Splatting has emerged as a new trend in surface reconstruction methods due to its camera-level novel view synthesis and accurate reconstruction. However, existing approaches mainly rely on dense views, often suffering from overfitting of Gaussian primitives that generate catastrophic floaters in sparse-view scenes, significantly degrading reconstruction accuracy. In this work, we propose PACG, a novel sparse-view surface reconstruction framework that integrates prior models with complementary densification-pruning. Specifically, PACG leverages the robust priors of Diffusion model and Feedforward model to initialize reconstruction. A coarse-to-fine geometry-aware loss ensures optimization stability, while gradient-uncollision densification and contribution-based pruning are employed during optimization to suppress floaters. PACG demonstrates superior performance over existing methods, achieving SOTA results on widely used DTU, Replica and BlendedMVS datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI