ATSplat：具有自適應標記擴展的緊湊前饋3D高斯潑濺

摘要

3D高斯泼溅（3DGS）通过优化三维空间中自由放置的基元并在重建不足区域自适应地加密这些基元，实现了高质量的新视点合成。然而，这种场景自适应容量分配能力在现有的前馈式3DGS方法中基本丧失——这些方法通常将高斯分布在输入像素上并沿相机光线进行提升。这种像素对齐的公式使得基元的数量和位置取决于图像分辨率和输入视点而非场景复杂度，导致高斯集密集且往往冗余。本文提出ATSplat，一种前馈式3DGS框架，通过自适应3D令牌恢复3DGS优化中的自适应分配能力。ATSplat首先将粗略的补丁级深度和相机线索提升为稀疏的3D锚点令牌，形成场景的紧凑骨架。每个令牌随后通过可学习的3D偏移量回归为局部高斯分布，将基元放置与输入图像网格解耦。自适应令牌扩展模块预测一个受渲染误差图监督的令牌级不确定性评分，并通过可学习的扩展层选择性地扩展高不确定性令牌。这种稀疏到自适应的公式使ATSplat能够将基元集中在具有挑战性的区域，同时保持紧凑的表示。在两个代表性数据集RealEstate10K和DL3DV上的实验表明，ATSplat在实现最先进渲染质量的同时，将高斯数量减少至密集前馈式3DGS方法的5.7倍以上。在12张512×960分辨率的输入图像下，ATSplat使用单块商用GPU可在不到一秒内完成重建，并以仅31.1万高斯在1136帧/秒（512×960）的速度渲染高质量新视点。

English

3D Gaussian Splatting (3DGS) achieves high-quality novel-view synthesis by optimizing freely placed primitives in 3D and adaptively densifying them in under-reconstructed regions. However, this scene-adaptive capacity allocation is largely lost in existing feed-forward 3DGS methods, which commonly regress Gaussians at input pixels and lift them along camera rays. Such pixel-aligned formulations make the number and placement of primitives depend on image resolution and input viewpoints rather than scene complexity, resulting in dense and often redundant Gaussian sets. We present ATSplat, a feed-forward 3DGS framework that restores the adaptive allocation capability of 3DGS optimization through Adaptive 3D Tokens. ATSplat first lifts coarse patch-level depth and camera cues into sparse 3D anchor tokens, forming a compact scaffold of the scene. Each token is then regressed into local Gaussians with learnable 3D offsets, decoupling primitive placement from input image grids. An Adaptive Token Expansion module predicts a token-level uncertainty score, supervised by rendering error maps, and selectively expands high-uncertainty tokens through learnable expansion layers. This sparse-to-adaptive formulation enables ATSplat to concentrate primitives in challenging regions while maintaining a compact representation. Experiments on two representative datasets, RealEstate10K and DL3DV, show that ATSplat achieves state-of-the-art rendering quality while reducing the number of Gaussians by more than 5.7times compared with dense feed-forward 3DGS methods. From 12 input images at 512 times 960 resolution, ATSplat completes reconstruction in less than a second using a single commercial GPU, and renders high-quality novel views at 1136 FPS (512 times 960) with only 311K Gaussians.