InfiniSplat

From images to 3D Gaussian scenes

Feed-forward reconstruction for novel-view rendering. Explore multi-view reconstruction (v2) or single-image reconstruction with optional LiDAR depth (v1).

	InfiniSplat v2 · Multi-view	InfiniSplat v1 · Single image / LiDAR
Input	Multiple images, with or without camera poses	One RGB image, optionally guided by LiDAR depth
Explore	Code and usage · Live demo	Code and usage · Live demo

---

🌐 InfiniSplat v2: Analyzing and Improving
Feed-Forward 3DGS from Any Views

Yongzhen Hu^* · Hao Yu^* · Jiawei Wang · Xianming Zeng · Jianyun Xu
Xingliang Liu · Ruizhen Hu · Xiaowei Zhou · Hujun Bao · Sida Peng^†

^* Equal contribution. ^† Corresponding author.

InfiniSplat v2 reconstructs 3D Gaussian scenes from multiple images, with or without camera poses, for novel-view rendering.

Code and usage · Installation · Inference guide · COLMAP guide · 360° panorama → 3DGS

---

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

SIGGRAPH Asia 2026 (ACM Transactions on Graphics)

Jiawei Wang^* · Hao Yu^* · Yongzhen Hu · Xinyi Yang · Tao Ni
Xin Zhan · Junbo Chen^† · Xiaowei Zhou · Ruizhen Hu · Sida Peng^†

^* Equal contribution. ^† Corresponding authors.

InfiniSplat v1 reconstructs 3D Gaussian scenes from a single RGB image, optionally guided by LiDAR depth, for novel-view rendering.

Code and usage · Installation · Inference guide

---

Getting started

From the repository root, run cd InfiniSplat_v2 for multi-view reconstruction or cd InfiniSplat_v1 for single-image / LiDAR-guided reconstruction, then follow that version's installation guide. Install each version in its own Python environment; their dependencies and weights differ.

License and Project Use

License: Project Registration License (PRL) v1.0

Use solely for academic research, education, evaluation, or personal purposes is free and does not require registration. Research results and publications may be published without registration.

Project use by companies, universities, or other organizations is free but requires prior registration, including non-commercial projects, internal R&D, testing, deployment, and production. Complete and accurate registration automatically grants permission; no approval or fee is required. Register each materially distinct project once.

Project use registration and Word template: Google Forms

V1 and v2 share the project license above. Third-party components retain their respective licenses and notices; see v2 component provenance.

Acknowledgments

See the v1 acknowledgments and v2 acknowledgments.

Panorama to 3DGS (v2)

Reconstruct a 360° panorama with the included small_empty_house example. Inspired by Enndee.