根据纹理动态分配3D高斯点，提升重建效率与质量
AdaptiveSplat:Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction
- 利用局部纹理信息判断细节复杂度，指导高斯点分配
- 在多个数据集上实现更高精度的重建，且无需推理时微调
- 适合追求高效实时3D重建的开发者与研究者
当前前馈式3D重建方法生成与像素对齐的高斯原始体，导致表示冗余。虽然直接剪枝可减少冗余，但会引入严重伪影，且常需推理时微调，违背前馈范式。已有研究表明，高频区域需更多高斯点，而低频区域可用更少点表示。受此启发，我们提出一种新方法，通过局部纹理信息显式控制高斯点数量。该方法包含三个关键组件：(1) 纹理估计，捕捉场景细节的空间变化；(2) 纹理感知剪枝，移除低频区域的冗余高斯点；(3) 自适应高斯头，预测保留原始体的修改属性，不破坏前馈特性。在RE10K、ACID、DL3DV、Tanks and Temples和DTU数据集上的实验验证了方法有效性，消融实验也证实了各组件贡献。
原文摘要 · Abstract (English)
Current feed-forward 3D reconstruction methods predict pixel aligned Gaussian primitives, resulting in highly redundant representations. A natural solution is to prune the redundant Gaussians, but naive pruning introduces severe artifacts and often requires inference time fine-tuning, breaking the feed-forward paradigm. Based on previous works, high frequency regions require more Gaussian primitives, while low frequency regions can be represented with significantly fewer primitives. Motivated by this, we propose a novel approach to explicitly control the number of Gaussians by leveraging local texture information. Our approach achieves this through three key components: (1) texture estimation to capture spatial variation in scene detail, (2) texture-aware pruning that removes redundant Gaussians from low frequency regions, and (3) an adaptive Gaussian head that predicts the modified attributes of the retained primitives without breaking the feed-forward paradigm. Experiments on RE10K, ACID, DL3DV, Tanks and Temples, and DTU demonstrate the effectiveness of our approach, while ablation studies validate the contributions of its key components.
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。