解决图像高斯点云变形中的几何错位问题，提升细节清晰度和运行速度。
GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
- 引入可变形偏移的迭代优化模块，主动修正空间错位。
- 通过隐式置信权重筛选可靠像素，避免有效信息丢失。
- 在保留高频细节的同时，推理速度提升2.13倍，适合高质量3D重建场景。
高斯点云渲染通过基于形变的技术取得了显著进展，但这类方法因几何不确定性导致像素级误差，造成形变图像的空间错位，干扰残差学习机制，限制了校正效果，尤其在细结构和高频细节上表现不佳。我们观察到，即使存在微小位移，有用视觉线索仍局部保留。为此提出几何感知可变形聚合（GADA），引入带有可变形偏移的迭代优化模块，主动修正空间错位并恢复被移位的视觉线索。同时，针对传统流程中可见性检测（阈值判断）常误删有效像素，以及多视角形变图像融合依赖简单均值聚合的问题，本方法结合隐式置信权重机制，选择性抑制不可靠证据。实验表明，该方法优于现有基于形变的高斯点云渲染，在保持高频质量的同时实现2.13倍的帧率提升。
原文摘要 · Abstract (English)
Gaussian Splatting has achieved significant improvements by incorporating warping-based techniques. However, such methods suffer from pixel-level inaccuracies due to uncertain geometry. This uncertainty leads to spatial misalignments in the warped images, which disrupt residual learning used in warping-based methods and fundamentally limit the gains of correction, particularly on thin structures and high-frequency details. Driven by our insight that useful visual cues are not lost but locally preserved under slight displacement, we propose Geometry-Aware Deformable Aggregation (GADA). This method introduces an iterative refinement module with deformable offsets to actively correct spatial misalignments and recover these displaced cues. Furthermore, to address the limitations of standard pipelines where visibility checks (i.e., thresholding) often discard valid pixels and multi-view warped image fusion relies on naive mean aggregation, our module is coupled with an implicit confidence weighting mechanism that selectively suppresses unreliable evidence. Consequently, our approach outperforms prior warping-based Gaussian Splatting, preserving high-frequency quality while achieving 2.13 times faster FPS.
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。