ATSplat: 基于自适应令牌扩展的紧凑前馈3D高斯泼溅

摘要

3D高斯溅射（3DGS）通过优化三维空间中自由放置的基元并在重建不足的区域自适应稠密化，实现了高质量的新视角合成。然而，现有前馈式3DGS方法在很大程度上丧失了这种场景自适应容量分配能力——这些方法通常在输入像素位置回归高斯体，并沿相机射线对其提升。这种像素对齐的公式使得基元的数量和布局依赖于图像分辨率和输入视角而非场景复杂度，导致生成的高斯集稠密且往往冗余。我们提出ATSplat，一种前馈式3DGS框架，通过自适应三维令牌恢复3DGS优化的自适应分配能力。ATSplat首先将粗略的块级深度和相机线索提升为稀疏的三维锚点令牌，形成场景的紧凑骨架。随后，每个令牌通过可学习的三维偏移回归为局部高斯体，从而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令牌级的不确定性分数（由渲染误差图监督），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RealEstate10K和DL3DV两个代表性数据集上的实验表明，ATSplat在实现最先进渲染质量的同时，相比稠密前馈式3DGS方法减少了超过5.7倍的高斯体数量。在512×960分辨率下使用12张输入图像时，ATSplat可在不到一秒内（单商用GPU）完成重建，并以1136 FPS（512×960）渲染高质量新视角，仅需311K个高斯体。

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.