Anysplat
See the Github repository: regarding installation instructions.
Modellquelle
- Art
- Other
- Dateigröße
- 2,74 GB
- Version
- vRevision d2e8c34
- Aktualisiert
- 17. Okt. 2026
- Downloads
- 7509
- Quelle
- Hugging Face
Quellenbeschreibung
AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
Project Website Paper GitHub Repo Hugging Face Model
Quick Start
See the Github repository: https://github.com/OpenRobotLab/AnySplat regarding installation instructions.
The model can then be used as follows:
from pathlib import Path
import torch
import os
import sys
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from src.misc.image_io import save_interpolated_video
from src.model.model.anysplat import AnySplat
from src.utils.image import process_image
# Load the model from Hugging Face
model = AnySplat.from_pretrained("anysplat_ckpt_v1")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = model.to(device)
model.eval()
for param in model.parameters():
param.requires_grad = False
# Load and preprocess example images (replace with your own image paths)
image_names = ["path/to/imageA.png", "path/to/imageB.png", "path/to/imageC.png"]
images = [process_image(image_name) for image_name in image_names]
images = torch.stack(images, dim=0).unsqueeze(0).to(device) # [1, K, 3, 448, 448]
b, v, _, h, w = images.shape
# Run Inference
gaussians, pred_context_pose = model.inference((images+1)*0.5)
pred_all_extrinsic = pred_context_pose['extrinsic']
pred_all_intrinsic = pred_context_pose['intrinsic']
save_interpolated_video(pred_all_extrinsic, pred_all_intrinsic, b, h, w, gaussians, image_folder, model.decoder)
Citation
@article{jiang2025anysplat,
title={AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views},
author={Jiang, Lihan and Mao, Yucheng and Xu, Linning and Lu, Tao and Ren, Kerui and Jin, Yichen and Xu, Xudong and Yu, Mulin and Pang, Jiangmiao and Zhao, Feng and others},
journal={arXiv preprint arXiv:2505.23716},
year={2025}
}
License
The code and models are licensed under the MIT License.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 17. Aug.
Modellartefakte
1 Artefakt
Modellartefakte
1 ArtefaktQuellenauszüge
2 Auszüge
Quellenauszüge
2 Auszüge--- license: mit pipeline_tag: image-to-3d --- # AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views [](https://city-super.github.io/anysplat/) [](https://arxiv.org/pdf/2505.23716) [](https://github.com/OpenRobotLab/AnySplat) [](https://huggingface.co/lhjiang/anysplat) ## Quick Start See the Github repository: https://github.com/OpenRobotLab/AnySplat regarding installation instructions. The model can then be used as follows: ```python from pathlib import Path import torch import os import sys sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from src.misc.image_io import save_interpolated_video from src.model.model.anysplat import AnySplat from src.utils.image import process_image # Load the model from Hugging Face model = AnySplat.from_pretrained("anysplat_ckpt_v1") device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model = model.to(device) model.eval() for param in model.parameters(): param.requires_grad = False # Load and preprocess example images (replace with your own image paths) image_names = ["path/to/imageA.png", "path/to/imageB.png", "path/to/imageC.png"] images = [process_image(image_name) for image_name in image_names] images = torch.stack(images, dim=0).unsqueeze(0).to(device) # [1, K, 3, 448, 448] b, v, _, h, w = images.shape # Run Inference gaussians, pred_context_pose = model.inference((images+1)*0.5) pred_all_extrinsic = pred_context_pose['extrinsic'] pred_all_intrinsic = pred_context_pose['intrinsic'] save_interpolated_video(pred_all_extrinsic, pred_all_intrinsic, b, h, w, gaussians, image_folder, model.decoder) ``` ## Citation ``` @article{jiang2025anysplat, title={AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views}, author={Jiang, Lihan and Mao, Yucheng and Xu, Linning and Lu, Tao and Ren, Kerui and Jin, Yichen and Xu, Xudong and Yu, Mulin and Pang, Jiangmiao and Zhao, Feng and others}, journal={arXiv preprint arXiv:2505.23716}, year={2025} } ``` ## License The code and models are l...
Source context: 7509 downloads · 14 likes · Pipeline image-to-3d · Repo lhjiang/anysplat
