InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Hao Yu* • Haotong Lin* • Jiawei Wang* • Jiaxin Li • Yida Wang • Xueyang Zhang • Yue Wang
Xiaowei Zhou • Ruizhen Hu • Sida Peng

📢 News

✨ Highlights

🎨 Arbitrary-Resolution 4K • 8K • 16K • Beyond

📐 Accurate Metric Depth Sparse Depth Prompts → Dense Accuracy

📷 Single-View NVS Hight-Quality • Large Viewpoint Shifts

📋 Open Source Roadmap

We are committed to making InfiniDepth open source! Here's our release plan:

🎯 Phase 1: Core Release

Model Weights - Pre-trained checkpoints for InfiniDepth variants

• Metric Depth Model
• Relative Depth Model

Inference Code - Easy-to-use interface for depth prediction

• Inference scripts and demo

🔧 Phase 2: Training & Evaluation

Training Code - Complete training pipeline

• Training scripts
• Configuration files
• Dataset preparation guides

Evaluation - Evaluation scripts and metrics

• Benchmark evaluation code
• Metrics computation
• Results visualization

Synth4K - Synthetic depth benchmark

• 4K-resolution ground-truth depth and high-frequency mask

🙏 Acknowledgments

We thank Yuanhong Yu, Gangwei Xu, Haoyu Guo and Chongjie Ye for their insightful discussions and valuable suggestions, and Zhen Xu for his dedicated efforts in curating the synthetic data.

📖 Citation

If you find InfiniDepth useful in your research, please consider citing:

@article{yu2026infinidepth,
    title={InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields},
    author={Hao Yu, Haotong Lin, Jiawei Wang, Jiaxin Li, Yida Wang, Xueyang Zhang, Yue Wang, Xiaowei Zhou, Ruizhen Hu and Sida Peng},
    booktitle={arXiv preprint},
    year={2026}
}

---

Thank you for your interest in InfiniDepth!

_{⭐ Star this repo if you find it interesting!}