TokenSplat: 令牌对齐的3D高斯散射用于前馈无姿态重建
TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
AI总结：
TokenSplat通过令牌对齐的3D高斯散射实现无姿态重建，结合可学习相机令牌和非对称双流解码器，提升重建保真度和姿态估计精度。
摘要：
我们提出了TokenSplat，一种用于从无姿态多视角图像中联合进行3D高斯重建和相机姿态估计的前馈框架。其核心是引入了一个令牌对齐的高斯预测模块，该模块在特征空间中直接对齐语义对应的跨视角信息。通过粗略令牌位置和融合置信度的引导，它聚合多尺度上下文特征，以实现长距离跨视角推理并减少重叠高斯的冗余。为进一步增强姿态鲁棒性并解耦视角线索与场景语义，TokenSplat采用可学习的相机令牌和一个非对称双流解码器（ADF-解码器），该解码器在相机和图像令牌之间强制方向约束的通信。这在前馈架构中保持了干净的因子分解，实现了连贯的重建和稳定的姿态估计，而无需迭代优化。广泛的实验表明，TokenSplat在无姿态设置中实现了更高的重建保真度和新视角合成质量，并显著提高了姿态估计的准确性，相比先前的无姿态方法有了显著提升。项目页面：https://kidleyh.github.io/tokensplat/。
英文摘要：
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/.
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。
