Sign in

Jakub Gregorek

@jakubgregorek.bsky.social
148 followers 407 following 8 posts

PhD student @ DTU Robotic Perception | 3D Vision | ML/AI

PostsRepliesMedia
Jakub Gregorek @jakubgregorek.bsky.social · 04/09/2026
🚀 Our paper is at #TAROS 2026 in Manchester, 7–9 Sep! 🤖   We present ShotcreteDepth 🏗️ — a bi-modal #dataset for robotic #depth #perception in dusty, low-light #shotcrete environments. 📄 arxiv.org/abs/2606.23152 🔗 github.com/dtu-pas/shot... @lanalpa.bsky.social @aicentre.dk
arxiv.org
ShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments
We introduce ShotcreteDepth, a bi-modal dataset from the construction domain that captures both an active shotcreting process and general construction environments. The dataset comprises stereo RGB im...
063
Jakub Gregorek @jakubgregorek.bsky.social · 01/06/2026
🚀 Theodora Kontogianni and I will be presenting our work "Need for Speed: Zero‑Shot Depth Completion with Single‑Step Diffusion” at #CVPR #NTIRE on June 4, 16:00–18:00, room 207. 🙋‍♂️Come say hello or explore dtu-pas.github.io/marigold-ssd/ @lanalpa.bsky.social @nandometzger.bsky.social @aicentre.dk
dtu-pas.github.io
Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion
031
Reposted by Jakub Gregorek
Lazaros Nalpantidis @lanalpa.bsky.social · 05/05/2026
Static neural networks are powerful, but the future of efficient AI lies in Dynamic Neural Networks (DyNNs)—models that adapt their structure or parameters during inference. 🏎️ ↔🐢
132
Reposted by Jakub Gregorek
Anton Obukhov @obukhov.ai · 15/05/2025
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 🧶👇
1448
Jakub Gregorek @jakubgregorek.bsky.social · 11/04/2025
Are you interested in joining our group? 🔥🚀
020
Reposted by Jakub Gregorek
Lazaros Nalpantidis @lanalpa.bsky.social · 20/02/2025
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...
efzu.fa.em2.oraclecloud.com
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,...
133
Reposted by Jakub Gregorek
Anton Obukhov @obukhov.ai · 04/02/2025
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!
274
Jakub Gregorek @jakubgregorek.bsky.social · 29/01/2025
🚀 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
invt.io
Join me at IEEE ICRA 2025 from 19-23 May 2025 in Atlanta, Georgia!
Learn more
010
Jakub Gregorek @jakubgregorek.bsky.social · 22/01/2025
🌟 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
steeredmarigold.github.io
Steered Marigold
Steering diffusion-based monocular estimator towards depth completion in a plug-and-play manner.
0113
Reposted by Jakub Gregorek
Fabio Montello @zioictus.bsky.social · 15/01/2025
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
arxiv.org
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...
175
Jakub Gregorek @jakubgregorek.bsky.social · 08/01/2025
Anyone interested in dynamic neural networks? 🧐
010
Reposted by Jakub Gregorek
Anton Obukhov @obukhov.ai · 19/12/2024
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 🧵
2197
Jakub Gregorek @jakubgregorek.bsky.social · 19/12/2024
🔥🔥🔥
030