Skip to content

Latest commit

 

History

History
130 lines (97 loc) · 4.98 KB

README.md

File metadata and controls

130 lines (97 loc) · 4.98 KB
Raw

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

     

Wenbo Hu1* †, Xiangjun Gao2*, Xiaoyu Li1* †, Sijie Zhao1, Xiaodong Cun1,
Yong Zhang1, Long Quan2, Ying Shan3, 1

1Tencent AI Lab 2The Hong Kong University of Science and Technology 3ARC Lab, Tencent PCG

arXiv preprint, 2024

🔆 Introduction

  • [24-9-28] Add full dataset inference and evaluation scripts for better comparison use. :-)
  • [24-9-25] 🤗🤗🤗 Add huggingface online demo DepthCrafter.
  • [24-9-19] Add scripts for preparing benchmark datasets.
  • [24-9-18] Add point cloud sequence visualization.
  • [24-9-14] 🔥🔥🔥 DepthCrafter is released now, have fun!

🤗 DepthCrafter can generate temporally consistent long-depth sequences with fine-grained details for open-world videos, without requiring additional information such as camera poses or optical flow.

🎥 Visualization

We provide some demos of unprojected point cloud sequences, with reference RGB and estimated depth videos. Please refer to our project page for more details.

365030500-ff625ffe-93ab-4b58-a62a-50bf75c89a92.mov

🚀 Quick Start

🛠️ Installation

  1. Clone this repo:
git clone https://github.com/Tencent/DepthCrafter.git
  1. Install dependencies (please refer to requirements.txt):
pip install -r requirements.txt

🤖 Gradio Demo

gradio app.py

🤗 Model Zoo

DepthCrafter is available in the Hugging Face Model Hub.

🏃‍♂️ Inference

1. High-resolution inference, requires a GPU with ~26GB memory for 1024x576 resolution:

  • Full inference (~0.6 fps on A100, recommended for high-quality results):

    python run.py  --video-path examples/example_01.mp4

  • Fast inference through 4-step denoising and without classifier-free guidance （~2.3 fps on A100）:

    python run.py  --video-path examples/example_01.mp4 --num-inference-steps 4 --guidance-scale 1.0

2. Low-resolution inference requires a GPU with ~9GB memory for 512x256 resolution:

  • Full inference (~2.3 fps on A100):

    python run.py  --video-path examples/example_01.mp4 --max-res 512

  • Fast inference through 4-step denoising and without classifier-free guidance (~9.4 fps on A100):

    python run.py  --video-path examples/example_01.mp4  --max-res 512 --num-inference-steps 4 --guidance-scale 1.0

🚀 Dataset Evaluation

Please check the benchmark folder.

  • To create the dataset we use in the paper, you need to run dataset_extract/dataset_extract_${dataset_name}.py.
  • Then you will get the csv files that save the relative root of extracted RGB video and depth npz files. We also provide these csv files.
  • Inference for all datasets scripts: 
    bash benchmark/infer/infer.sh
    (Remember to replace the input_rgb_root and saved_root with your own path.)
  • Evaluation for all datasets scripts: 
    bash benchmark/eval/eval.sh
    (Remember to replace the pred_disp_root and gt_disp_root with your own path.)

🤝 Contributing

  • Welcome to open issues and pull requests.
  • Welcome to optimize the inference speed and memory usage, e.g., through model quantization, distillation, or other acceleration techniques.

📜 Citation

If you find this work helpful, please consider citing:

@article{hu2024-DepthCrafter,
            author      = {Hu, Wenbo and Gao, Xiangjun and Li, Xiaoyu and Zhao, Sijie and Cun, Xiaodong and Zhang, Yong and Quan, Long and Shan, Ying},
            title       = {DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos},
            journal     = {arXiv preprint arXiv:2409.02095},
            year        = {2024}
    }