MuGS实现跨基线的通用新视角合成，提升复杂场景重建质量。
MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction
- 融合多视图立体与单目深度特征，增强泛化表征能力。
- 通过概率体引导深度融合，在多种基线设置下达最优性能。
- 支持零样本迁移，适合复杂真实场景的快速建模应用。
我们提出多基线通用高斯点云重建方法（MuGS），一种高效的前馈式新视角合成框架，能有效处理从稀疏输入视图到不同基线（小基线与大基线）的多样化设置。通过融合多视图立体（MVS）与单目深度估计（MDE）特征，增强模型在复杂场景下的表征能力；设计投影-采样机制实现深度特征融合，构建精细概率体积以指导特征图回归；引入参考视图损失，提升几何精度与优化效率。采用3D高斯表示加速训练与推理，同时提升渲染质量。MuGS在多种基线设置下均达到当前最优表现，涵盖简单物体（DTU）至复杂室内外场景（RealEstate10K）。还在LLFF与Mip-NeRF 360数据集上展现良好零样本性能。代码已开源：https://github.com/EuclidLou/MuGS。
原文摘要 · Abstract (English)
We present Multi-Baseline Gaussian Splatting (MuGS), a generalized feed-forward approach for novel view synthesis that effectively handles diverse baseline settings, including sparse input views with both small and large baselines. Specifically, we integrate features from Multi-View Stereo (MVS) and Monocular Depth Estimation (MDE) to enhance feature representations for generalizable reconstruction. Next, We propose a projection-and-sampling mechanism for deep depth fusion, which constructs a fine probability volume to guide the regression of the feature map. Furthermore, We introduce a reference-view loss to improve geometry and optimization efficiency. We leverage 3D Gaussian representations to accelerate training and inference time while enhancing rendering quality. MuGS achieves state-of-the-art performance across multiple baseline settings and diverse scenarios ranging from simple objects (DTU) to complex indoor and outdoor scenes (RealEstate10K). We also demonstrate promising zero-shot performance on the LLFF and Mip-NeRF 360 datasets. Code is available at https://github.com/EuclidLou/MuGS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。