WildDet3D

WildDet3D predicts three-dimensional boxes from a single image.

任务: 3d detection
尺寸: l at 1008 px
安装: pip install "libreyolo[hf]"
支持层级: 兄弟层级，自 v1.6.0 起。一个独立的产品面，有自己的工厂和契约。
上游: WildDet3D，由 Allen Institute for AI 发布，采用 SAM License 许可。论文、源码
许可: 代码采用 MIT，权重采用 SAM License。商用

Install

bash

pip install "libreyolo[hf]"

Predict

Python

from libreyolo import LibreWildDet3D, SAMPLE_IMAGEfrom PIL import Imageimport numpy as np # Requires the separately installed upstream runtime.model = LibreWildDet3D(device="cpu")# Approximate pinhole intrinsics for the original image size.# Replace with your camera's measured 3x3 calibration for real geometry.width, height = Image.open(SAMPLE_IMAGE).sizef = max(width, height)intrinsics = np.array([[f, 0, width / 2], [0, f, height / 2], [0, 0, 1]], dtype=np.float32)result = model.predict(SAMPLE_IMAGE, intrinsics=intrinsics, text="person")print(result.boxes3d)

WildDet3D accepts text, box or point prompts and requires original-image camera intrinsics. Install its separate upstream runtime and provide runtime_path and runtime_python when they are outside the active environment.

result.boxes3d holds centers, dimensions and wxyz quaternions in camera coordinates, plus confidence, class and intrinsics. Plotting projects cuboids into the image. Training, validation, tracking and export are not supported. See 3D detection.

Licensing

请检查你所下载的具体权重在 Hugging Face 仓库中的许可。LibreYOLO 组织里的每个检查点都附有许可，同一家族内也不一定相同。该仓库是权威来源；以下摘要说明本页上次验证时适用的情况。

这里只说明涉及的许可证，不构成法律意见。如果答案对商用很重要，请自行阅读许可证并咨询法律顾问。

原始工作: WildDet3D, Allen Institute for AI
上游许可: SAM License
上游来源: github.com/allenai/WildDet3D
LibreYOLO 代码: MIT
权重: 采用 SAM License 许可，重新发布在 huggingface.co/LibreYOLO
解读: The upstream runtime and checkpoint retain the custom SAM License, including its field-of-use restrictions.

Citation

@misc{huang2026wilddet3dscalingpromptable3d,
      title={WildDet3D: Scaling Promptable 3D Detection in the Wild}, 
      author={Weikai Huang and Jieyu Zhang and Sijun Li and Taoyang Jia and Jiafei Duan and Yunqian Cheng and Jaemin Cho and Matthew Wallingford and Rustin Soraki and Chris Dongjoo Kim and Shuo Liu and Donovan Clay and Taira Anderson and Winson Han and Ali Farhadi and Bharath Hariharan and Zhongzheng Ren and Ranjay Krishna},
      year={2026},
      eprint={2604.08626},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2604.08626}, 
}

复制自作者在 raw.githubusercontent.com/allenai/WildDet3D/main/README.md 上提供的引用块。