Rong Li^*,   Yuhao Dong^*,   Tianshuai Hu^*,   Ao Liang^*,   Youquan Liu^*,   Dongyue Lu^*
Liang Pan,   Lingdong Kong^†,   Junwei Liang^‡,   Ziwei Liu^‡

^*Equal contribution   ^†Project lead   ^‡Corresponding authors

• Cross-Platform: First 3D grounding dataset spanning vehicle, drone, and quadruped platforms
• Large-Scale: Large-scale annotated samples across diverse real-world scenarios
• Multi-Modal: Synchronized RGB, LiDAR, and language annotations
• Challenging: Complex outdoor environments with varying object densities and viewpoints
• Reproducible: Unified evaluation protocols and baseline implementations

If you find our work helpful, please consider citing:

@inproceedings{li2025_3eed,
    title     = {{3EED}: Ground Everything Everywhere in {3D}},
    author    = {Rong Li and Yuhao Dong and Tianshuai Hu and Ao Liang and Youquan Liu and Dongyue Lu and Liang Pan and Lingdong Kong and Junwei Liang and Ziwei Liu},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    volume    = {38},
    year      = {2025}
}

📄 For detailed dataset statistics and analysis, please refer to our paper.

• [2025.10] Dataset and code are now publicly available on HuggingFace and GitHub! 📦
• [2025.09] 3EED has been accepted to NeurIPS 2025 Dataset and Benchmark Track! 🎉

• Highlights
• Statistics
• News
• Table of Contents
• Installation
  • Environment Setup
  • Custom CUDA Operators
• Pretrained Models
  • Language Encoder
• Dataset
  • Download
  • Dataset Structure
• Quick Start
  • Training
  • Evaluation
  • Visualization
  • Baseline Checkpoints
• License
• Acknowledgements
  • Codebase & Methods
  • Dataset Sources

We support both CUDA 11 and CUDA 12 environments. Choose the one that matches your system:

cd ops/teed_pointnet/pointnet2_batch
python setup.py develop

cd ../roiaware_pool3d
python setup.py develop

Download the RoBERTa-base checkpoint from HuggingFace and move it to data/roberta_base.

Download the 3EED dataset from HuggingFace:

🔗 Dataset Link: https://huggingface.co/datasets/RRRong/3EED

After extraction, organize your dataset as follows:

data/3eed/
├── drone/                    # Drone platform data
│   ├── scene-0001/
│   │   ├── 0000_0/
│   │   │   ├── image.jpg
│   │   │   ├── lidar.bin
│   │   │   └── meta_info.json
│   │   └── ...
│   └── ...
├── quad/                     # Quadruped platform data
│   ├── scene-0001/
│   └── ...
├── waymo/                    # Vehicle platform data
│   ├── scene-0001/
│   └── ...
├── roberta_base/            # Language model weights
└── splits/                  # Train/val split files
    ├── drone_train.txt
    ├── drone_val.txt
    ├── quad_train.txt
    ├── quad_val.txt
    ├── waymo_train.txt
    └── waymo_val.txt

Train the baseline model on different platform combinations:

# Train on all platforms (recommended for best performance)
bash scripts/train_3eed.sh

# Train on single platform
bash scripts/train_waymo.sh   # Vehicle only
bash scripts/train_drone.sh   # Drone only
bash scripts/train_quad.sh    # Quadruped only

Output:

• Checkpoints: logs/Train_<datasets>_Val_<datasets>/<timestamp>/
• Training logs: logs/Train_<datasets>_Val_<datasets>/<timestamp>/log.txt
• TensorBoard logs: logs/Train_<datasets>_Val_<datasets>/<timestamp>/tensorboard/

Evaluate trained models on validation sets:

Quick Evaluation:

# Evaluate on all platforms
bash scripts/val_3eed.sh

# Evaluate on single platform
bash scripts/val_waymo.sh    # Vehicle
bash scripts/val_drone.sh    # Drone
bash scripts/val_quad.sh     # Quadruped

⚠️ Before running evaluation:

1. Update --checkpoint_path in the script to point to your trained model
2. Ensure the validation dataset is downloaded and properly structured

Output:

• Results saved to: <checkpoint_dir>/evaluation/Val_<dataset>/<timestamp>/

Visualize predictions with 3D bounding boxes overlaid on point clouds:

# Visualize prediction results
python utils/visualize_pred.py

Visualization Output:

• 🟢 Ground Truth: Green bounding box
• 🔴 Prediction: Red bounding box

Output Structure:

visualizations/
├── waymo/
│   ├── scene-0001_frame-0000/
│   │   ├── pointcloud.ply
│   │   ├── pred/gt_bbox.ply
│   │   └── info.txt
│   └── ...
├── drone/
└── quad/

Baseline models and predictions are available at: Huggingface

This repository is released under the Apache 2.0 License (see LICENSE).

We sincerely thank the following projects and teams that made this work possible:

• BUTD-DETR - Bottom-Up Top-Down DETR for visual grounding
• WildRefer - Wild referring expression comprehension

• Waymo Open Dataset - Vehicle platform data
• M3ED - Drone and quadruped platform data

😎 Awesome	Projects
	3D and 4D World Modeling: A Survey [GitHub Repo] - [Project Page] - [Paper]
	WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World [GitHub Repo] - [Project Page] - [Paper]
	LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences [GitHub Repo] - [Project Page] - [Paper]
	Are VLMs Ready for Autonomous Driving? A Study from Reliability, Data & Metric Perspectives [GitHub Repo] - [Project Page] - [Paper]
	Perspective-Invariant 3D Object Detection [GitHub Repo] - [Project Page] - [Paper]
	DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes [GitHub Repo] - [Project Page] - [Paper]