zju3dv/InfiniSplat

[SIGGRAPH Asia 2026][TOG 2026] InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Python

346

8 commits

updated Sep 11, 2026

See the code

README

🌌 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 Demo

📣 News

[2026-07] 🎉 InfiniSplat has been conditionally accepted to SIGGRAPH Asia 2026 (Journal Track)!

[2026-07] 🎉 Inference code for RGB-only and depth-guided 3D Gaussian reconstruction is available now!

🧩 What can InfiniSplat do?

InfiniSplat supports two practical modes for single-image 3D Gaussian reconstruction:

CapabilityInputOutput
Monocular 3D Gaussian ReconstructionRGB Image3DGS
Depth-Sensor-Guided 3D Gaussian ReconstructionRGB Image + Depth3DGS

⚙️ Installation

Please see INSTALL.md for environment setup and checkpoint download.

🚀 Inference

RGB Only

Run a single image:

python -m src.demo.infer_batch_images --input examples/data/rgb_demo/pexels-masi.jpg

Run a directory using the bundled examples:

python -m src.demo.infer_batch_images --input examples/data/rgb_demo

Depth-Sensor-Guided Reconstruction

Run a single RGB and depth pair with matching filename stems in the same directory:

python -m src.demo.infer_batch_images \
  --mode lidar \
  --input examples/data/lidar_demo/eth3d_kicker.png

Run the bundled RGB and depth pairs:

python -m src.demo.infer_batch_images \
  --mode lidar \
  --input examples/data/lidar_demo

See docs/inference.md for camera parameters, output control, and other optional arguments.

🖥️ Web Demo

The local Gradio demo provides RGB reconstruction, staged PLY and standalone HTML downloads, and an interactive Gaussian viewer. After preparing the inference environment, launch it with:

python demo.py

Open http://127.0.0.1:7860 in a browser. The demo reuses checkpoints/infinisplat_rgb.ckpt when available and otherwise downloads the released RGB checkpoint from PLUS-WAVE/InfiniSplat. Set INFINISPLAT_CHECKPOINT to use a checkpoint at another path.

The hosted version is available on the Hugging Face Space.

📄 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

🙏 Acknowledgments

We sincerely thank the authors of DINOv3, Depth Pro, InfiniDepth, and gsplat for their excellent work. InfiniSplat is built on top of these projects.


Thanks

Thank you for your interest in InfiniSplat!

⭐ Star this repo if you find it interesting!

Significant stargazers

Andrew Carr

108 followers · starred Aug 2026

Cypherpunk Samurai

170 followers · starred Aug 2026

zju3dv/InfiniSplat

[SIGGRAPH Asia 2026][TOG 2026] InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Python

346

8 commits

updated Sep 11, 2026

See the code

README

🌌 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 Demo

📣 News

[2026-07] 🎉 InfiniSplat has been conditionally accepted to SIGGRAPH Asia 2026 (Journal Track)!

[2026-07] 🎉 Inference code for RGB-only and depth-guided 3D Gaussian reconstruction is available now!

🧩 What can InfiniSplat do?

InfiniSplat supports two practical modes for single-image 3D Gaussian reconstruction:

CapabilityInputOutput
Monocular 3D Gaussian ReconstructionRGB Image3DGS
Depth-Sensor-Guided 3D Gaussian ReconstructionRGB Image + Depth3DGS

⚙️ Installation

Please see INSTALL.md for environment setup and checkpoint download.

🚀 Inference

RGB Only

Run a single image:

python -m src.demo.infer_batch_images --input examples/data/rgb_demo/pexels-masi.jpg

Run a directory using the bundled examples:

python -m src.demo.infer_batch_images --input examples/data/rgb_demo

Depth-Sensor-Guided Reconstruction

Run a single RGB and depth pair with matching filename stems in the same directory:

python -m src.demo.infer_batch_images \
  --mode lidar \
  --input examples/data/lidar_demo/eth3d_kicker.png

Run the bundled RGB and depth pairs:

python -m src.demo.infer_batch_images \
  --mode lidar \
  --input examples/data/lidar_demo

See docs/inference.md for camera parameters, output control, and other optional arguments.

🖥️ Web Demo

The local Gradio demo provides RGB reconstruction, staged PLY and standalone HTML downloads, and an interactive Gaussian viewer. After preparing the inference environment, launch it with:

python demo.py

Open http://127.0.0.1:7860 in a browser. The demo reuses checkpoints/infinisplat_rgb.ckpt when available and otherwise downloads the released RGB checkpoint from PLUS-WAVE/InfiniSplat. Set INFINISPLAT_CHECKPOINT to use a checkpoint at another path.

The hosted version is available on the Hugging Face Space.

📄 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

🙏 Acknowledgments

We sincerely thank the authors of DINOv3, Depth Pro, InfiniDepth, and gsplat for their excellent work. InfiniSplat is built on top of these projects.


Thanks

Thank you for your interest in InfiniSplat!

⭐ Star this repo if you find it interesting!

Significant stargazers

Andrew Carr

108 followers · starred Aug 2026

Cypherpunk Samurai

170 followers · starred Aug 2026

Languages

Python

93.6%

Cuda

5.7%