无需姿态和先验，实现跨场景高精度3D重建
SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting
- 结合自监督深度与姿态估计，实现无标注数据下的3D重建
- 在RealEstate10K等数据集上超越现有方法，几何与外观质量更优
- 适合需要泛化能力的工业级3D建模场景
我们提出SelfSplat，一种新型3D Gaussian Splatting模型，可在无姿态、无3D先验条件下，从多视角图像中实现通用3D重建。该任务因缺乏真值数据与学习到的几何信息，且需无需微调即可达到高质量重建，传统方法难以应对。我们的模型通过将显式3D表示与自监督深度及姿态估计有效结合，实现姿态精度与3D重建质量的相互提升。此外，引入匹配感知姿态估计网络与深度精修模块，增强多视图几何一致性，确保重建更准确稳定。我们在大型真实世界数据集RealEstate10K、ACID和DL3DV上评估，结果表明SelfSplat在外观与几何质量上均优于现有最先进方法，并展现出强跨数据集泛化能力。大量消融实验与分析验证了所提方法的有效性。代码与预训练模型已公开于https://gynjn.github.io/selfsplat/
原文摘要 · Abstract (English)
We propose SelfSplat, a novel 3D Gaussian Splatting model designed to perform pose-free and 3D prior-free generalizable 3D reconstruction from unposed multi-view images. These settings are inherently ill-posed due to the lack of ground-truth data, learned geometric information, and the need to achieve accurate 3D reconstruction without finetuning, making it difficult for conventional methods to achieve high-quality results. Our model addresses these challenges by effectively integrating explicit 3D representations with self-supervised depth and pose estimation techniques, resulting in reciprocal improvements in both pose accuracy and 3D reconstruction quality. Furthermore, we incorporate a matching-aware pose estimation network and a depth refinement module to enhance geometry consistency across views, ensuring more accurate and stable 3D reconstructions. To present the performance of our method, we evaluated it on large-scale real-world datasets, including RealEstate10K, ACID, and DL3DV. SelfSplat achieves superior results over previous state-of-the-art methods in both appearance and geometry quality, also demonstrates strong cross-dataset generalization capabilities. Extensive ablation studies and analysis also validate the effectiveness of our proposed methods. Code and pretrained models are available at https://gynjn.github.io/selfsplat/
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。