无需迭代优化，一键完成3D重建与相机位姿估计。
TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
- 用特征空间对齐机制，跨视角聚合上下文信息。
- 重建精度和新视角合成质量优于现有无位姿方法。
- 适合需要快速、稳定3D重建的实时应用开发。
我们提出 TokenSplat，一种从无位姿多视角图像中联合进行3D高斯重建与相机位姿估计的前馈框架。核心是引入了特征空间对齐的高斯预测模块，直接在特征层面对齐跨视角的语义对应信息。该模块基于粗粒度标记位置与融合置信度，聚合多尺度上下文特征，实现长距离跨视角推理，并减少重叠高斯点带来的冗余。为进一步增强位姿鲁棒性并解耦视角线索与场景语义，TokenSplat采用可学习的相机标记和非对称双流解码器（ADF-Decoder），在相机与图像标记间施加方向性约束通信，保持前馈架构内清晰的因子分解，实现无需迭代优化的连贯重建与稳定位姿估计。大量实验表明，TokenSplat 在无位姿设定下实现了更高的重建保真度与新视角合成质量，并显著提升位姿估计精度，优于以往无位姿方法。项目页面：https://kidleyh.github.io/tokensplat/
原文摘要 · Abstract (English)
We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a Token-aligned Gaussian Prediction module that aligns semantically corresponding information across views directly in the feature space. Guided by coarse token positions and fusion confidence, it aggregates multi-scale contextual features to enable long-range cross-view reasoning and reduce redundancy from overlapping Gaussians. To further enhance pose robustness and disentangle viewpoint cues from scene semantics, TokenSplat employs learnable camera tokens and an Asymmetric Dual-Flow Decoder (ADF-Decoder) that enforces directionally constrained communication between camera and image tokens. This maintains clean factorization within a feed-forward architecture, enabling coherent reconstruction and stable pose estimation without iterative refinement. Extensive experiments demonstrate that TokenSplat achieves higher reconstruction fidelity and novel-view synthesis quality in pose-free settings, and significantly improves pose estimation accuracy compared to prior pose-free methods. Project page: https://kidleyh.github.io/tokensplat/.
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。