Discover and explore top open-source AI tools and projects—updated daily.
Depth estimation for open-world videos (CVPR 2025 Highlight)
Top 28.4% on SourcePulse
DepthCrafter generates temporally consistent, high-fidelity depth sequences for open-world videos without requiring camera poses or optical flow. It is targeted at researchers and developers in computer vision and VFX, offering improved quality and speed over existing methods.
How It Works
DepthCrafter employs a novel approach to produce long, consistent depth sequences by leveraging a diffusion model trained on extensive video data. This method inherently handles temporal coherence and fine-grained details, eliminating the need for explicit motion estimation or camera pose information, which simplifies the pipeline and broadens applicability.
Quick Start & Requirements
git clone https://github.com/Tencent/DepthCrafter.git
followed by pip install -r requirements.txt
.gradio app.py
.Highlighted Details
Maintenance & Community
Licensing & Compatibility
Limitations & Caveats
1 month ago
Inactive