mviola/nuImages-cam-front
Viewer • Updated • 16.4k • 76
🚢 Shipping
Massimiliano Viola
mviola
P(doom) <0.1%
AI & ML interests
Computer Vision • 3D • Generative Models • Robotics
Recent Activity
updated a dataset 9 days ago
mviola/nuImages-cam-front published a dataset 9 days ago
mviola/nuImages-cam-front authored a paper 19 days ago
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse ObservationsOrganizations
updated a
dataset 9 days ago
published a
dataset 9 days ago
authored 2
papers 19 days ago
upvoted a paper 19 days ago
upvoted a collection 5 months ago
Upload PE-AV architecture diagram
1
#614 opened 5 months ago
by mviola
upvoted a collection 6 months ago
upvoted an article 9 months ago
Article
Gotchas in Tokenizer Behavior Every Developer Should Know
qgallouedec
• • 72 liked a
Space 12 months ago
Test split
#2 opened about 1 year ago
by mviola
liked a
dataset about 1 year ago
upvoted an article about 1 year ago
Article
cocogold: training Marigold for text-grounded segmentation
pcuenq
• • 30 liked a
Space almost 2 years ago
upvoted a paper almost 2 years ago
reacted to toshas's post with 😎 almost 2 years ago
Post
1490
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.