| title | ZipSplat: Fewer Gaussians, Better Splats |
|---|---|
| authors | Alexander Veicht, Sunghwan Hong, Dániel Baráth, Marc Pollefeys |
| date | 2026-06-03 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.05102 |
| affiliation | ETH Zurich |
| upvotes | 22 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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{https://veichta.com/zipsplat}}. |
cite
@misc{veicht2026zipsplat,
title={ZipSplat: Fewer Gaussians, Better Splats},
author={Alexander Veicht and Sunghwan Hong and Dániel Baráth and Marc Pollefeys},
year={2026},
eprint={2606.05102},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.05102}
}