We introduce AnySplat, a feed forward network for novel view synthesis from uncalibrated image collections. In contrast to traditional neural rendering pipelines that demand known camera poses and per scene optimization, or recent feed forward methods that buckle under the computational weight of dense views, our model predicts everything in one shot. A single forward pass yields a set of 3D Gaussian primitives encoding both scene geometry and appearance, and the corresponding camera intrinsics and extrinsics for each input image. This unified design scales effortlessly to casually captured, multi view datasets without any pose annotations. In extensive zero shot evaluations, AnySplat matches the quality of pose aware baselines in both sparse and dense view scenarios while surpassing existing pose free approaches. Moreover, it greatly reduce rendering latency compared to optimization based neural fields, bringing real time novel view synthesis within reach for unconstrained capture settings.Project page: https://city-super.github.io/anysplat/
@article{arxiv.2505.23716,
title = {AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views},
author = {Lihan Jiang and Yucheng Mao and Linning Xu and Tao Lu and Kerui Ren and Yichen Jin and Xudong Xu and Mulin Yu and Jiangmiao Pang and Feng Zhao and Dahua Lin and Bo Dai},
journal= {arXiv preprint arXiv:2505.23716},
year = {2025}
}