多模态先验引导的重要性采样用于稀疏视图新视图合成中的分层高斯点云
Multimodal-Prior-Guided Importance Sampling for Hierarchical Gaussian Splatting in Sparse-View Novel View Synthesis
AI总结：
本文提出多模态先验引导的重要性采样方法，用于稀疏视图新视图合成中的分层高斯点云，通过融合光度残差、语义和几何先验，提升重建质量。
摘要：
我们提出了多模态先验引导的重要性采样作为稀疏视图新视图合成中分层三维高斯点云（3DGS）的核心机制。我们的采样器融合互补的提示{ -- }光度渲染残差、语义先验和几何先验{ -- }以产生一个稳健的、局部可恢复性估计，直接驱动在哪里注入细粒度高斯点。围绕这个采样核心，我们的框架包括（1）从粗到细的高斯表示，该表示用稳定的粗层编码全局形状，并在多模态指标指示可恢复细节的地方选择性地添加细粒度原语；和（2）一种几何感知的采样和保留策略，该策略将细化集中在几何上关键和复杂的区域，同时保护在欠约束区域中新增的原语免受过早剪枝。通过优先考虑由一致的多模态证据支持的区域，而不是仅凭原始残差，我们的方法减轻了因纹理引起的过拟合误差，并抑制了姿态/外观不一致带来的噪声。在多样化的稀疏视图基准上的实验表明，我们的方法实现了最先进的重建效果，最高可达DTU上的+0.3 dB PSNR。
英文摘要：
We present multimodal-prior-guided importance sampling as the central mechanism for hierarchical 3D Gaussian Splatting (3DGS) in sparse-view novel view synthesis. Our sampler fuses complementary cues { -- } photometric rendering residuals, semantic priors, and geometric priors { -- } to produce a robust, local recoverability estimate that directly drives where to inject fine Gaussians. Built around this sampling core, our framework comprises (1) a coarse-to-fine Gaussian representation that encodes global shape with a stable coarse layer and selectively adds fine primitives where the multimodal metric indicates recoverable detail; and (2) a geometric-aware sampling and retention policy that concentrates refinement on geometrically critical and complex regions while protecting newly added primitives in underconstrained areas from premature pruning. By prioritizing regions supported by consistent multimodal evidence rather than raw residuals alone, our method alleviates overfitting texture-induced errors and suppresses noise from pose/appearance inconsistencies. Experiments on diverse sparse-view benchmarks demonstrate state-of-the-art reconstructions, with up to +0.3 dB PSNR on DTU.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
