InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

SIGGRAPH Asia 2026 (ACM Transactions on Graphics)

Jiawei Wang^1* Hao Yu^1* Yongzhen Hu¹ Xinyi Yang¹ Tao Ni² Xin Zhan² Junbo Chen^2†

Xiaowei Zhou³ Ruizhen Hu⁴ Sida Peng^1†

¹Zhejiang University ²UDeer.ai ³State Key Laboratory of CAD&CG, Zhejiang University ⁴Shenzhen University

^*Equal contribution ^†Corresponding authors

TL;DR

InfiniSplat is a feed-forward single-image 3D Gaussian Splatting framework for large-baseline novel view synthesis.
It moves Gaussian generation from pixel-aligned image grids toward surface-aligned supports guided by monocular geometry.
A query-conditioned implicit Gaussian decoder predicts Gaussian attributes on sampled supports, producing more coherent surfaces under large viewpoint changes.

Demo

Qualitative Visualization

In-the-wild

In-the-wild RGB input

WASD + Mouse to move view, ESC to exit

Qualitative Comparison

RGB qualitative comparison under large viewpoint changes. InfiniSplat-RGB produces fewer visible cracks and more coherent scene structures than feed-forward baselines.

With sparse LiDAR points as additional input, InfiniSplat-LiDAR produces substantially better novel-view rendering quality than ADGaussian.

InfiniSplat V2

Multi-view Feed-Forward Gaussian Splatting

Visit InfiniSplat V2

WASD + Mouse to move view, ESC to exit

Loading V2 viewer

Citation

@article{wang2026infinisplat,
  title={InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis},
  author={Wang, Jiawei and Yu, Hao and Hu, Yongzhen and Yang, Xinyi and Ni, Tao and Zhan, Xin and Chen, Junbo and Zhou, Xiaowei and Hu, Ruizhen and Peng, Sida},
  journal={arXiv preprint arXiv:2608.02437},
  year={2026}
}