---
title: VideoLDCM
canonical_url: "https://www.modelscope.cn/models/RunminZhang/VideoLDCM"
md_url: "https://www.modelscope.cn/models/RunminZhang/VideoLDCM.md"
repository: RunminZhang/VideoLDCM
chinese_name: VideoLDCM
last_updated: 2026-06-11
license: apache-2.0
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 1
stars: 0
tags:
  - video-depth-completion
  - sparse-depth-completion
  - data-refinement
  - visual-geometry
  - vigeo
  - "arxiv:2605.30060"
---

# VideoLDCM

> VideoLDCM - RunminZhang 在 ModelScope 开源的模型。VideoLDCM is the sparse-depth completion and refinement model used for ViGeo data refinement. It takes an RGB image sequence and sparse depth maps, then runs MoGe, Poisson completion, and VideoLDCM refinement…

RunminZhang/VideoLDCM 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: RunminZhang/VideoLDCM
- **License**: apache-2.0
- **Tags**: video-depth-completion, sparse-depth-completion, data-refinement, visual-geometry, vigeo, arxiv:2605.30060
- **Downloads**: 1
- **Stars**: 0
- **Last updated**: 2026-06-11

Source: https://www.modelscope.cn/models/RunminZhang/VideoLDCM

---

# VideoLDCM

VideoLDCM is the sparse-depth completion and refinement model used for ViGeo
data refinement. It takes an RGB image sequence and sparse depth maps, then
runs MoGe, Poisson completion, and VideoLDCM refinement through the
`videoldcm.infer` interface.

The checkpoint in this repository is `videoldcm.pt`.

## Installation

```bash
conda create -n vigeo python=3.10 -y
conda activate vigeo

pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu126
pip install xformers==0.0.31 --index-url https://download.pytorch.org/whl/cu126

git clone https://github.com/aigc3d/ViGeo.git
cd ViGeo
pip install -r requirements.txt
pip install -r requirements_refine.txt
pip install -e .
```

## Quick Start

```python
import torch

from videoldcm import videoldcm
from utils import load_depth_sequence, load_image_sequence

image_paths = ["path/to/image_000.png", "path/to/image_001.png"]
sparse_depth_paths = ["path/to/sparse_depth_000.npy", "path/to/sparse_depth_001.npy"]
device = torch.device("cuda")

image = load_image_sequence(image_paths).to(device)                # [S, 3, H, W]
sparse_depth = load_depth_sequence(sparse_depth_paths).to(device)  # [S, 1, H, W]

completion_model = videoldcm.from_pretrained("pkqbajng/VideoLDCM").eval().to(device)

with torch.inference_mode():
    output = completion_model.infer(image=image, sparse_depth=sparse_depth)

refined_depth = output["depth_pred"]  # [S, 1, H, W]
points = output["points_pred"]        # [S, H, W, 3]
confidence = output["conf_pred"]      # [S, 1, H, W]
```

`infer` does not run the sparse-depth mismatch filter. For the explicit data
refinement pipeline with mismatch filtering and Poisson completion, see the
[ViGeo main branch README](https://github.com/aigc3d/ViGeo/tree/main#videoldcm-data-refinement).

## Links

- ViGeo project page: https://pkqbajng.github.io/ViGeo/
- Paper: https://arxiv.org/abs/2605.30060
- GitHub repository: https://github.com/aigc3d/ViGeo

## License

Apache License 2.0.