无干扰的可泛化3D高斯点散布
Distractor-free Generalizable 3D Gaussian Splatting
AI总结：
DGGS通过无干扰的可泛化3D高斯点散布框架，解决跨场景训练中的干扰问题，提升重建能力和掩码预测准确性。
摘要：
我们提出了DGGS，一种新的框架，旨在解决此前未被探索的挑战：无干扰的可泛化3D高斯点散布（3DGS）。它通过在跨场景可泛化训练设置中减轻由干扰数据引起的3D不一致性和训练不稳定性，同时使3DGS和参考中的干扰掩码能够进行前向推断。为实现这些目标，DGGS在训练阶段提出了一种场景无关的基于参考的掩码预测和细化模块，有效消除了干扰对训练稳定性的影响。此外，我们通过一种新的两阶段推理框架对参考进行评分和重新选择，辅以一种干扰修剪机制，进一步去除残留的干扰3DGS原始影响。在真实数据和我们合成数据上的大量前向实验表明，DGGS在处理新干扰场景时的重建能力。此外，我们的可泛化掩码预测甚至在准确性上超过了现有场景特定训练方法。主页是https://github.com/bbbbby-99/DGGS。
英文摘要：
We present DGGS, a novel framework that addresses the previously unexplored challenge: $\textbf{Distractor-free Generalizable 3D Gaussian Splatting}$ (3DGS). It mitigates 3D inconsistency and training instability caused by distractor data in the cross-scenes generalizable train setting while enabling feedforward inference for 3DGS and distractor masks from references in the unseen scenes. To achieve these objectives, DGGS proposes a scene-agnostic reference-based mask prediction and refinement module during the training phase, effectively eliminating the impact of distractor on training stability. Moreover, we combat distractor-induced artifacts and holes at inference time through a novel two-stage inference framework for references scoring and re-selection, complemented by a distractor pruning mechanism that further removes residual distractor 3DGS-primitive influences. Extensive feedforward experiments on the real and our synthetic data show DGGS's reconstruction capability when dealing with novel distractor scenes. Moreover, our generalizable mask prediction even achieves an accuracy superior to existing scene-specific training methods. Homepage is https://github.com/bbbbby-99/DGGS.
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。
