Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
Paper
•
2412.13389
•
Published
•
6
CompVis Community
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
compvis-community's activity
toshas
authored
a
paper
6 days ago
Post
1155
Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you!
Depth Completion addresses sparse, incomplete, or noisy measurements from photogrammetry or sensors like LiDAR. Sparse points aren’t just hard for humans to interpret — they also hinder downstream tasks.
Traditionally, depth completion was framed as image-guided depth interpolation. We leverage Marigold, a diffusion-based monodepth model, to reframe it as sparse-depth-guided depth generation. How the turntables! Check out the paper anyway 👇
🌎 Website: https://marigolddepthcompletion.github.io/
🤗 Demo: prs-eth/marigold-dc
📕 Paper: https://arxiv.org/abs/2412.13389
👾 Code: https://github.com/prs-eth/marigold-dc
Team ETH Zürich: Massimiliano Viola ( @mviola ), Kevin Qu ( @KevinQu7 ), Nando Metzger ( @nandometzger ), Bingxin Ke ( @Bingxin ), Alexander Becker, Konrad Schindler, and Anton Obukhov ( @toshas ). We thank
Hugging Face for their continuous support.
Depth Completion addresses sparse, incomplete, or noisy measurements from photogrammetry or sensors like LiDAR. Sparse points aren’t just hard for humans to interpret — they also hinder downstream tasks.
Traditionally, depth completion was framed as image-guided depth interpolation. We leverage Marigold, a diffusion-based monodepth model, to reframe it as sparse-depth-guided depth generation. How the turntables! Check out the paper anyway 👇
🌎 Website: https://marigolddepthcompletion.github.io/
🤗 Demo: prs-eth/marigold-dc
📕 Paper: https://arxiv.org/abs/2412.13389
👾 Code: https://github.com/prs-eth/marigold-dc
Team ETH Zürich: Massimiliano Viola ( @mviola ), Kevin Qu ( @KevinQu7 ), Nando Metzger ( @nandometzger ), Bingxin Ke ( @Bingxin ), Alexander Becker, Konrad Schindler, and Anton Obukhov ( @toshas ). We thank
Hugging Face for their continuous support.
hjzheng
authored
a
paper
9 days ago
penfever
authored
a
paper
14 days ago
toshas
authored
a
paper
23 days ago
holynski
authored
a
paper
27 days ago
lvwerra
authored
a
paper
about 2 months ago
holynski
authored
a
paper
2 months ago
penfever
authored
2
papers
3 months ago
rinong
authored
a
paper
3 months ago
dariog
authored
3
papers
3 months ago
The MAMe Dataset: On the relevance of High Resolution and Variable Shape image properties
Paper
•
2007.13693
•
Published
Boosting Healthcare LLMs Through Retrieved Context
Paper
•
2409.15127
•
Published
•
19
Present and Future Generalization of Synthetic Image Detectors
Paper
•
2409.14128
•
Published
•
18
penfever
authored
a
paper
3 months ago
holynski
authored
a
paper
4 months ago
rishistyping
authored
a
paper
5 months ago
holynski
authored
a
paper
5 months ago
sea-snell
authored
2
papers
5 months ago