Lightnews — Scholar-powered news

Reposted by Jakub Gregorek

Anton Obukhov @obukhov.ai · May 15

Big Marigold update!
Last year, we showed how to turn Stable Diffusion 2 into a SOTA depth estimator with a few synthetic samples and 2–3 days on just 1 GPU.
Today's release features:
🏎️ 1-step inference
🔢 New modalities
🫣 High resolution
🧨 Diffusers support
🕹️ New demos
🧶👇

1 8 45

Jakub Gregorek @jakubgregorek.bsky.social · Apr 11

Are you interested in joining our group? 🔥🚀

Lazaros Nalpantidis @lanalpa.bsky.social · Apr 11

Join us and revolutionize Life Science Lab Automation! 🎓🤖💉

I am hiring a Postdoc in Robotics and Computer Vision for Life Science Laboratory Automation, in Copenhagen, Denmark.

Is that you? 🙋‍♀️
efzu.fa.em2.oraclecloud.com/hcmUI/Candid...

Postdoc in Robotics and Computer Vision for Life Science Laboratory Automation - DTU Electro

As part of a joint research collaboration between DTU and Novo Nordisk, we are looking for a postdoc to join our multidisciplinary research program focusing on the interplay between AI-Protein design,...

efzu.fa.em2.oraclecloud.com

2

Reposted by Jakub Gregorek

Lazaros Nalpantidis @lanalpa.bsky.social · Feb 20

I am hiring a Postdoctoral Researcher to work on Computer Vision for Autonomous Robots in Life Science Automation.

#ComputerVision #Robotics #LabAutomation

Apply here: efzu.fa.em2.oraclecloud.com/hcmUI/Candid...

Postdoc in Autonomous Robots and Perception for Protein Design Laboratories - DTU Electro

As part of a joint research collaboration between DTU and Novo Nordisk, we are looking for a postdoc to join our multidisciplinary research program focusing on the interplay between AI-Protein design,...

efzu.fa.em2.oraclecloud.com

1 3 3

Reposted by Jakub Gregorek

Anton Obukhov @obukhov.ai · Feb 4

MDEC Challenge update! The 4th Monocular Depth Estimation Workshop at #CVPR2025 will be accepting submissions in two phases:
🚀 Dev phase: Feb 1 - Mar 1
🎯 Final phase: Mar 1 - Mar 21
Website: jspenmar.github.io/MDEC/
🌐 Codalab: codalab.lisn.upsaclay.fr/competitions...

Bring your best depth!

2 4 7

Jakub Gregorek @jakubgregorek.bsky.social · Jan 29

🚀 Our depth completion method SteeredMarigold will be presented at #ICRA2025 🚀. Meet @lanalpa.bsky.social and me in Atlanta between 19-23 May! invt.io/1exb0qqtfdj #robotics #depthcompletion #depthestimation

Join me at IEEE ICRA 2025 from 19-23 May 2025 in Atlanta, Georgia!

Learn more

invt.io

1

Jakub Gregorek @jakubgregorek.bsky.social · Jan 22

🌟 Exciting News! 🌟 We're thrilled to announce the launch of our website for SteeredMarigold 🚀 steeredmarigold.github.io. Our cutting-edge method helps to overcome limitations of depth sensors by completing missing areas in the depth maps 🤖. The code is coming! #DepthCompletion #DepthEstimation

Steered Marigold

Steering diffusion-based monocular estimator towards depth completion in a plug-and-play manner.

steeredmarigold.github.io

3 11

Reposted by Jakub Gregorek

Fabio Montello @zioictus.bsky.social · Jan 15

Our paper “A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion" is out as preprint!

By myself, @sscardapane.bsky.social, @rgring.bsky.social and @lanalpa.bsky.social

📄 arxiv.org/abs/2501.07451

A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion

Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that d...

arxiv.org

1 5 7

Jakub Gregorek @jakubgregorek.bsky.social · Jan 8

Anyone interested in dynamic neural networks? 🧐

Fabio Montello @zioictus.bsky.social · Jan 8

First little project of the year: an awesome collection of papers on Dynamic Neural Networks for Computer Vision and Sensor Fusion!

Each paper comes with a brief summary and code link.

👉 github.com/DTU-PAS/awes...

GitHub - DTU-PAS/awesome-dynn-for-cv: Awesome collection of DyNN papers for Computer Vision and Sensor Fusion applications :sparkles:

Awesome collection of DyNN papers for Computer Vision and Sensor Fusion applications :sparkles: - DTU-PAS/awesome-dynn-for-cv

github.com

1

Reposted by Jakub Gregorek

Anton Obukhov @obukhov.ai · Dec 19

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! Details 🧵

2 7 19

Jakub Gregorek @jakubgregorek.bsky.social · Dec 19

🔥🔥🔥

Lazaros Nalpantidis @lanalpa.bsky.social · Dec 19

Great to see similar ideas to our own “SteeredMarigold” zero-shot depth completion method!

arxiv.org/abs/2409.10202

SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps

Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods st...

arxiv.org

3

Jakub Gregorek @jakubgregorek.bsky.social · Nov 28

The Marigold paper has been an absolute inspiration. We can't wait for the arXiv release!

3