SparseSplat通过稀疏化高斯分布，用更少的点实现顶尖渲染质量。
SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction
- 根据场景结构动态调整高斯密度，生成稀疏紧凑的3D地图。
- 仅用22%的高斯点达到顶尖渲染效果，1.5%仍保持合理质量。
- 适合需要轻量化3D重建的实时应用或资源受限场景。
前向3D高斯喷溅（3DGS）虽显著提升渲染质量，但其空间均匀且冗余的3DGS映射限制了下游重建任务的集成。我们提出SparseSplat，首个能根据场景结构和局部信息丰富度自适应调整高斯密度的前向3DGS模型，生成高度紧凑的3DGS映射。为此，我们引入基于熵的随机采样策略，在纹理缺失区域生成大而稀疏的高斯点，在信息丰富的区域分配小而密集的高斯点。此外，设计专用点云网络，高效编码局部上下文并解码为3DGS属性，解决了通用3DGS优化流程与前向模型之间的感受野不匹配问题。大量实验表明，SparseSplat仅需22%的高斯点即可达到顶尖渲染质量，仅用1.5%的高斯点仍可保持合理渲染效果。
原文摘要 · Abstract (English)
Recent progress in feed-forward 3D Gaussian Splatting (3DGS) has notably improved rendering quality. However, the spatially uniform and highly redundant 3DGS map generated by previous feed-forward 3DGS methods limits their integration into downstream reconstruction tasks. We propose SparseSplat, the first feed-forward 3DGS model that adaptively adjusts Gaussian density according to scene structure and information richness of local regions, yielding highly compact 3DGS maps. To achieve this, we propose entropy-based probabilistic sampling, generating large, sparse Gaussians in textureless areas and assigning small, dense Gaussians to regions with rich information. Additionally, we designed a specialized point cloud network that efficiently encodes local context and decodes it into 3DGS attributes, addressing the receptive field mismatch between the general 3DGS optimization pipeline and feed-forward models. Extensive experimental results demonstrate that SparseSplat can achieve state-of-the-art rendering quality with only 22% of the Gaussians and maintain reasonable rendering quality with only 1.5% of the Gaussians. Project page: https://victkk.github.io/SparseSplat-page/.
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。