Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict one Gaussian per input pixel, tying the representation budget to camera resolution rather than scene complexity. A flat wall and a richly textured object thus produce equally many Gaussians despite very different geometric needs. We propose ZipSplat, a token-based feed-forward model that decouples Gaussian placement from the pixel grid. A multi-view backbone extracts dense visual tokens, and k-means clustering compresses them into a compact set of scene tokens. Cross- and self-attention refine these tokens, and a lightweight MLP decodes each into a group of Gaussians with unconstrained 3D positions. Because clustering is applied at inference, a single trained model spans the quality-efficiency curve without retraining. ZipSplat operates without ground-truth poses or intrinsics, yet sets a new state of the art on DL3DV and RealEstate10K with ${\sim}6{\times}$ fewer Gaussians than pixel-aligned methods, surpassing the best pose-free baseline by 2.1dB and 1.2dB PSNR, respectively. It further generalizes zero-shot to Mip-NeRF360 and ScanNet++, outperforming all comparable baselines. Our project page is at https://veichta.com/zipsplat.

翻译：前馈式三维高斯泼溅方法能够在单次前向传播中，从有姿态或无姿态图像重建场景，但当前方法为每个输入像素预测一个高斯，将表示预算与相机分辨率而非场景复杂度绑定。因此，一面平坦墙壁与一个纹理丰富的物体会产生数量相同的高斯，尽管其几何需求大相径庭。我们提出ZipSplat，一种基于令牌的前馈模型，将高斯放置与像素网格解耦。多视角主干提取密集视觉令牌，k均值聚类将其压缩为紧凑的场景令牌集。交叉注意力与自注意力优化这些令牌，轻量级MLP将每个令牌解码为一组位置不受限的三维高斯。由于推理时应用聚类，单个训练模型无需重新训练即可覆盖质量-效率曲线。ZipSplat无需真实姿态或内参，却以比像素对齐方法少约6倍的高斯，在DL3DV和RealEstate10K上分别以2.1dB和1.2dB PSNR超越最佳无姿态基线，创下新纪录。它还能零样本泛化至Mip-NeRF360和ScanNet++，优于所有可比基线。我们的项目页面位于https://veichta.com/zipsplat。