Downloads · 30 days
4
1% of all-time downloads
Yukinoo/NexusGS-llff
NexusGS-llff is a machine learning model from Yukinoo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for NexusGS.
This model has been pushed to the Hub using the PytorchModelHubMixin integration: - Code: https://github.com/USMizuki/NexusGS - Paper: https://arxiv.org/abs/2503.18794 - Docs: https://usmizuki.github.io/NexusGS/
Downloads · 30 days
4
1% of all-time downloads
All-time downloads
468
Public
Repo size
333 MB
Likes
0
Public
Click a slice to open those files.
.safetensors285 MB · 100%
From the Hugging Face model README
This model has been pushed to the Hub using the PytorchModelHubMixin integration:
This repository hosts multiple Gaussian Splatting models trained on the LLFF dataset using the NexusGS framework. Each scene is stored as a separate Git branch, and can be loaded individually via the HFGaussianModel class.
This model repository contains pre-trained Gaussian Splatting models for 8 LLFF scenes:
fernflowerfortresshornsleavesorchidsroomtrexEach branch contains:
├── config.json
├── model.safetensors
The main branch contains all model files for convenience, named as:
config-<scene>.json
model-<scene>.safetensors
To use a specific scene model, use the from_pretrained method from scene.hf_gaussian_model.HFGaussianModel:
from scene.hf_gaussian_model import HFGaussianModel
# Load the 'fern' scene
model = HFGaussianModel.from_pretrained("Yukinoo/NexusGS-llff", revision="fern")
Replace "fern" with any of the available scenes:
"flower", "fortress", "horns", "leaves", "orchids", "room", "trex"
The HFGaussianModel loader is implemented in the NexusGS repository.
This utility enables seamless integration with Hugging Face Hub.
from scene.hf_gaussian_model import HFGaussianModel
model = HFGaussianModel.from_pretrained("Yukinoo/NexusGS-llff", revision="scene_name")
This model follows the license of the NexusGS repository. Please check the original repo for details.
For issues, contributions, or suggestions, feel free to open a discussion or pull request.