无需优化，单次前向传播即可从稀疏视角重建可动物体的3D结构和关节参数。
ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views
- 提出像素级关节图表示，实现关节参数与几何结构联合前向推断。
- 在PartNet-Mobility数据集上达到领先精度，速度比基线快400倍以上。
- 适合快速生成可动物体3D模型，尤其适用于大规模场景建模。
从稀疏视角图像中重建可动物体是一项病态问题，需同时推断几何结构与运动骨架。现有基于NeRF和3D高斯溅射（3DGS）的方法通常依赖密集视图或强先验（如深度图、关节类型、预设关节数），且需耗时的逐物体优化。本文提出ArtSplat，首个面向可动物体的前向3D高斯溅射框架，仅通过一次前向传播，即可从多状态稀疏视图中同时重建几何结构与关节参数。为应对单次前向推断的挑战，我们引入像素级关节图表示，将关节参数估计集成至前向流程；并设计跨状态注意力（CSA）机制，通过状态令牌有效捕捉不同构型间的离散运动。在PartNet-Mobility数据集上，涵盖68个可动物体及单/多关节配置，实验表明，ArtSplat在几何与关节估计上均达竞争性性能，且速度超过基线400倍。
原文摘要 · Abstract (English)
Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing methods for articulated object reconstruction based on NeRF and 3D Gaussian Splatting (3DGS) typically rely on dense views or strong priors (e.g., depth maps, joint types, predefined number of joints) and require costly per-object optimization. In this paper, we propose ArtSplat, the first feed-forward framework for articulated 3D Gaussian Splatting. It reconstructs both geometry and joint parameters from sparse multi-view images across multiple articulation states in a single forward pass. To address the challenges of single-pass articulated reconstruction, we introduce a per-pixel joint map representation that enables the integration of joint parameter estimation into the feed-forward pipeline. We further propose a Cross-State Attention (CSA) mechanism with state tokens, which effectively captures discrete motion across input states. Experiments on 68 articulated objects from PartNet-Mobility, including both single- and multi-joint configurations, demonstrate that ArtSplat achieves competitive performance in both geometry and joint estimation, while being over 400 times faster than baselines.
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。