Author | Lightnews

Simone Schaub-Meyer @simoneschaub.bsky.social · 11d

🎉 Today, Simon Kiefhaber will present our ICCV oral paper on how to make optical flow estimators more efficient (faster inference and lower memory usage) with state-of-the-art accuracy:

🌍 visinf.github.io/recover

Talk: Tue 09:30 AM, Kalakaua Ballroom
Poster: Tue 11:45 AM, Exhibit Hall I #76

1 5

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · 15d

📢Excited to share our IROS 2025 paper “Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model”!

Work by Jannik Endres, @olvrhhn.bsky.social, Charles Cobière, @simoneschaub.bsky.social, @stefanroth.bsky.social and Alexandre Alahi.

1 5 5

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · 13d

[1/8] We are presenting four main conference papers, two workshop papers, and a workshop at @iccv.bsky.social 2025 in Hawaii! 🎉🏝

1 3 7

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Sep 29

🎓 Looking for a PhD position in computer vision? Apply to the European Laboratory for Learning & Intelligent Systems (ELLIS) and work with @stefanroth.bsky.social & @simoneschaub.bsky.social! Join the info session on Oct 1.

@ellis.eu @tuda.bsky.social

ellis.eu/news/ellis-p...

ELLIS PhD Program: Call for Applications 2025

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

ellis.eu

6 10

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Sep 23

We are presenting five papers at the DAGM German Conference on Pattern Recognition (GCPR, @gcpr-by-dagm.bsky.social) in Freiburg this week!

1 2 6

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Sep 23

Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation (GCPR 2025)

by @dustin-carrion.bsky.social, @stefanroth.bsky.social, and @simoneschaub.bsky.social

🌍: visinf.github.io/emat

Poster: Wednesday, 03:30 PM, Postern 8

1 1 5

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Sep 23

Removing Cost Volumes from Optical Flow Estimators (ICCV 2025 Oral)

by @skiefhaber.de, @stefanroth.bsky.social, and @simoneschaub.bsky.social

🌍: visinf.github.io/recover

Poster: Friday, 10:30 AM, Poster 14

1 1 5

Reposted by Simone Schaub-Meyer

Sweta Mahajan @swetamahajan.bsky.social · Sep 16

🚀 Open-Mic Opinions! 🚀

We welcome you to voice your opinion on the state of XAI. You get 5 minutes to speak (in-person only) during the workshop.

📷 Submit your proposals here: lnkd.in/d7_EWKXp

For more details: lnkd.in/dpYWVYXS

@iccv.bsky.social #ICCV2025 #eXCV

1 4 7

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Aug 29

Some impressions from our VISINF summer retreat at Lizumer Hütte in the Tirol Alps — including a hike up Geier Mountain and new research ideas at 2,857 m! 🇦🇹🏔️

5 15

Reposted by Simone Schaub-Meyer

Sweta Mahajan @swetamahajan.bsky.social · Aug 13

🚨Deadline Approaching! 🚨

Non-Proceedings track closes in 2 days!

Be sure to submit on time!

We are awaiting your submissions!

More info at: excv-workshop.github.io

@iccv.bsky.social #ICCV2025 #eXCV

1 1 1

Reposted by Simone Schaub-Meyer

Robin Hesse @robinhesse.bsky.social · Jun 26

Got a strong XAI paper rejected from ICCV? Submit it to our ICCV eXCV Workshop today—we welcome high-quality work!
🗓️ Submissions open until June 26 AoE.
📄 Got accepted to ICCV? Congrats! Consider our non-proceedings track.
#ICCV2025 @iccv.bsky.social

9 20

Reposted by Simone Schaub-Meyer

Sukrut Rao @sukrutrao.bsky.social · Jun 14

Join us in taking stock of the state of the field of explainability in computer vision, at our Workshop on Explainable Computer Vision: Quo Vadis? at #ICCV2025!

@iccv.bsky.social

Call for papers at the eXCV workshop at ICCV 2025.

1 5 13

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Jun 11

We are presenting 3 papers at #CVPR2025!

1 2 7

Reposted by Simone Schaub-Meyer

TU Darmstadt @tuda.bsky.social · May 22

Reasonable Artificial Intelligence und The Adaptive Mind: Die TU Darmstadt wird im Rahmen der Exzellenzstrategie des Bundes und der Länder mit gleich zwei geförderten Clusterprojekten ausgezeichnet. Ein Meilenstein für unsere Universität! www.tu-darmstadt.de/universitaet...

Zwei Exzellenzcluster für die TU Darmstadt

Großer Erfolg für die Technische Universität Darmstadt: Zwei ihrer Forschungsprojekte werden künftig als Exzellenzcluster gefördert. Die Exzellenzkommission im Wettbewerb der prestigeträchtigen Exzell...

www.tu-darmstadt.de

10 32

Reposted by Simone Schaub-Meyer

Martin Mundt @martinmundt.bsky.social · May 23

"Reasonable AI" got selected as a cluster of excellence www.tu-darmstadt.de/universitaet...

Overwhelmingly happy to be part of RAI & continue working with the smart minds at TU Darmstadt & hessian.AI, while also seeing my new home at Uni Bremen achieve a historic success in the excellence strategy!

1 3 8

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Apr 4

📢 #CVPR2025 Highlight: Scene-Centric Unsupervised Panoptic Segmentation 🔥

We present CUPS, the first unsupervised panoptic segmentation method trained directly on scene-centric imagery.
Using self-supervised features, depth & motion, we achieve SotA results!

🌎 visinf.github.io/cups

1 6 22

Reposted by Simone Schaub-Meyer

Martin Mundt @martinmundt.bsky.social · Feb 18

Why has continual ML not had its breakthrough yet?

In our new collaborative paper w/ many amazing authors, we argue that “Continual Learning Should Move Beyond Incremental Classification”!

We highlight 5 examples to show where CL algos can fail & pinpoint 3 key challenges

arxiv.org/abs/2502.11927

3 10

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Jan 31

🏔️⛷️ Looking back on a fantastic week full of talks, research discussions, and skiing in the Austrian mountains!

11 31

Reposted by Simone Schaub-Meyer

Andreas Geiger @andreasgeiger.bsky.social · Jan 15

Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.

12 26 190

Reposted by Simone Schaub-Meyer

TU Darmstadt @tuda.bsky.social · Jan 13

Verstehen, was KI-Modelle können – und was nicht: Interview mit @simoneschaub.bsky.social, Early-Career-Forscherin im Clusterprojekt „RAI“ (Reasonable Artificial Intelligence).
"RAI" ist eines der Projekte, mit denen sich die TUDa um einen Exzellenzcluster bewirbt.
www.youtube.com/watch?v=2VAm...

Verstehen, was KI-Modelle können und was nicht: RAI-Forschende Dr. Simone Schaub-Meyer im Interview

YouTube video by Technische Universität Darmstadt

www.youtube.com

3 14

Simone Schaub-Meyer @simoneschaub.bsky.social · Jan 8

Hi Julian, just joined bluesky, I am working on XAI in Computer Vision, would be great to be added to the list as well, thanks

1 1

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Dec 13

Want to learn about how model design choices affect the attribution quality of vision models? Visit our #NeurIPS2024 poster on Friday afternoon (East Exhibition Hall A-C #2910)!

Paper: arxiv.org/abs/2407.11910
Code: github.com/visinf/idsds

1 7 21

Reposted by Simone Schaub-Meyer

Visual Inference Lab @visinf.bsky.social · Nov 28

Our work, "Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals" is accepted at TMLR! 🎉

visinf.github.io/primaps/

PriMaPs generate masks from self-supervised features, enabling to boost unsupervised semantic segmentation via stochastic EM.

1 7 17

Reposted by Simone Schaub-Meyer

TU Darmstadt @tuda.bsky.social · Mar 4

Die DFG hat Dr. Simone Schaub-Meyer ins Emmy Noether-Programm aufgenommen. Schaub-Meyer will Methoden entwickeln, die das Verständnis für weit verbreitete Modelle der #KI in der Bild-und Videoanalyse erhöhen www.tu-darmstadt.de/universitaet...

Neue Emmy Noether-Gruppe erforscht erklärbare KI für die Bild-und Videoanalyse

Die Deutsche Forschungsgemeinschaft hat Dr. Simone Schaub-Meyer in ihr Emmy Noether-Programm aufgenommen. Mit ihrer neuen Nachwuchsgruppe will sie Methoden erforschen und entwickeln, die das Verständn...

www.tu-darmstadt.de

1 2