Hermann Blum

107 Followers
211 Following
69 Posts
roboticist, assistant professor @ Uni Bonn & Lamarr Institute
interested in self-learning & autonomous robots, likes all the messy hardware problems of real-world experiments
websitehttps://hermannblum.net/
labhttps://rpl.uni-bonn.de/

CroCoDL Workshop at #ICCV, next talk coming up in Room 301B:

16.30 - 17.00: Torsten Sattler on Vision Localization Across Modalities

full schedule: https://localizoo.com/workshop/

CroCoDL Workshop at #ICCV, next talk coming up in Room 301B:

14.15 - 14.45: Ayoung Kim on Bridging heterogeneous sensors for robust and generalizable localization

full schedule: https://localizoo.com/workshop/

CroCoDL Workshop at #ICCV, next talk coming up in Room 301B:

13.15 - 13.45: Gabriela Csurka on Privacy Preserving Visual Localization

Attending #ICCV? Join the CroCoDL workshop this afternoon!

https://localizoo.com/workshop/

Speakers: Gabriela Csurka, Ayoung Kim, David Caruso, Torsten Sattler

This is the first time in a while I am creating a new talk. This will be fun!
I'll be up later today at the Visual SLAM workshop at @roboticsscisys.bsky.socialโ€ฌ

https://buff.ly/ADHxPsX

#RSS #Robotics #SLAM

Turns out aria-glasses are a very useful tool to demonstrate actions to robots: Based on egocentric video, we track dynamic changes in a scene graph and use the representation to replay or plan interactions for robots.
๐Ÿ”— https://behretj.github.io/LostAndFound/
๐Ÿ“„ https://arxiv.org/abs/2411.19162

#robotics #computervision #mobilemanipulation #CV #ethzurich #unibonn #lamarrinstitute

Lost & Found: Updating Dynamic 3D Scene Graphs from Egocentric Observations

our demo team is getting ready #ECCV2024

Are you also a bit exhausted after #ICRA submission week? Let us brighten your day with a real "SpotLight" ๐Ÿ’ก

๐Ÿ”— https://timengelbracht.github.io/SpotLight/
๐Ÿ“„ https://arxiv.org/abs/2409.11870

We detect and generate interaction for almost any light switch and can then map which switch turns on which light.

#Robotics #ETH #UniBonn #LamarrInstitute

SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection

Deformable Neural Radiance Fields creates free-viewpoint portraits (nerfies) from casually captured videos.

Exciting Day! My labโ€˜s first robot got delivered ๐Ÿคฉ
Thanks to all speakers, contributors and helpers for a nice workshop today! Recordings are online for anybody interested https://www.youtube.com/channel/UCSUL2K_bHSS-YrYySlKfupQ
Bevor Sie zu YouTube weitergehen