Visual Inference Lab

I am one of the potential advisors for this PhD position in our #DAAD funded AI graduate school ELIZA (eliza.school), which connects seven #ELLIS units in Germany. If you are interested in working with one of my colleagues or with me (in computer vision & deep learning), please consider applying.

📢 NeurIPS 2025 Spotlight 📢

Can we embed motion into image representations?

FlowFeat embeds optical flow into pixel-level representations, which results in sharp feature grids, especially for dynamic objects.

Project website: tum-vision.github.io/flowfeat

With Anna Sonnweber and Daniel Cremers.

📢 Join @tuda.bsky.social as a PhD/Postdoc in the new project HAICC - Human–AI Collaboration for Cybersecurity!

Explore how LLM–based AI agents and humans can jointly analyse security data and rethink cybersecurity architectures - supervised by Iryna Gurevych, @stefanroth.bsky.social, and many more!

Attending #Neurips2025? Get your personalized Scholar Inbox conference program now to easily navigate the poster sessions and find what you are looking for:
www.scholar-inbox.com/conference/n...

@neuripsconf.bsky.social is two weeks away!

📢 Stop missing great workshop speakers just because the workshop wasn’t on your radar. Browse them all in one place:
robinhesse.github.io/workshop_spe...

(also available for @euripsconf.bsky.social)

#NeurIPS #EurIPS

📢🎓 We have open PhD positions in Computer Vision & Machine Learning at @tuda.bsky.social and @hessianai.bsky.social within the Reasonable AI Cluster of Excellence — supervised by @stefanroth.bsky.social, @simoneschaub.bsky.social and many others!

www.career.tu-darmstadt.de/tu-darmstadt...

🎉 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

Interested in 3D DINO features from a single image or unsupervised scene understanding?🦖
Come by our SceneDINO poster at NeuSLAM today 14:15 (Kamehameha II) or Tue, 15:15 (Ex. Hall I 627)!
W/ Jevtić @fwimbauer.bsky.social @olvrhhn.bsky.social Rupprecht, @stefanroth.bsky.social @dcremers.bsky.social

[8/8] 2nd Workshop on Explainable Computer Vision: Quo Vadis?


🌍 excv-workshop.github.io


Sun 8:00 AM — 5:00 PM, Ballroom A

[7/8] Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation

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



🌍 visinf.github.io/emat
📄 arxiv.org/abs/2507.23642
💻 github.com/visinf/emat

Poster: Sun 4:40 PM - Exhibit Hall II #73

[6/8]

📄 arxiv.org/abs/2509.02545


Talk: Sun 9:30 AM, 306 A

Poster: Sun 10:00 AM - Exhibit Hall II

[6/8] Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery (Oral at ILR+G Workshop)

by Xinrui Gong*, @olvrhhn.bsky.social *, @christophreich.bsky.social , Krishnakant Singh, @simoneschaub.bsky.social , @dcremers.bsky.social @stefanroth.bsky.social

[5/8] ART: Adaptive Relation Tuning for Generalized Relation Prediction

by Gopika Sudhakaran, Hikaru Shindo, Patrick Schramowski, @simoneschaub.bsky.social, @kerstingaiml.bsky.social, @stefanroth.bsky.social

📄 arxiv.org/abs/2507.23543

Poster: Wed 2:45 PM, Exhibit Hall I #1501

[4/8] Activation Subspaces for Out-of-Distribution Detection

by Baris Zongur, @robinhesse.bsky.social, @stefanroth.bsky.social

📄 arxiv.org/abs/2508.21695

Poster: Tue 11:45 AM, Exhibit Hall I #326

[3/8]
Poster: Tue 3:15 PM, Exhibit Hall I #627
Invited
Invited poster at NeuSLAM workshop: Sun 2:15 PM, 304 A/Exhibit Hall II

[3/8] Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

by @jev-aleks.bsky.social *, @christophreich.bsky.social *, @fwimbauer.bsky.social , @olvrhhn.bsky.social , Christian Rupprecht, @stefanroth.bsky.social, @dcremers.bsky.social

🌍 visinf.github.io/scenedino/

[2/8] Removing Cost Volumes from Optical Flow Estimators (Oral)

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

🌍 visinf.github.io/recover

Talk: Tue 09:30 AM, Kalakaua Ballroom

Poster: Tue 11:45 AM, Exhibit Hall I #76

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

🇨🇳 Meet us at IROS 2025:
- Oral presentation: Thu, 23 Oct, 10:40–10:45 AM, Room 309, at Session ThAT9 – Object Detection, Segmentation and Categorization 5
- Poster session: Starting at 11:10 AM in the same room

For more information:

🌍Project page: vita-epfl.github.io/DFI-OmniSter...
📄 Paper: arxiv.org/pdf/2503.23502
💻 Code: github.com/vita-epfl/DF...
🎥 Video: www.youtube.com/watch?v=CHDQ...

TLDR: Given images captured by two vertically stacked omnidirectional cameras, DFI–OmniStereo integrates a pre-trained monocular depth foundation model into an iterative stereo matching approach. DFI–OmniStereo improves depth estimation accuracy, significantly outperforming the previous SotA.

📢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.

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...

🎓 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...

Activation Subspaces for Out-of-Distribution Detection (ICCV 2025)

by Baris Zongur, @robinhesse.bsky.social, and @stefanroth.bsky.social

📄: arxiv.org/abs/2508.21695

Talk: Wednesday, 1:30 PM, Oral Session 2
Poster: Wednesday, 3:30 PM, Poster 12

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

Scene-Centric Unsupervised Panoptic Segmentation (CVPR 2025 Highlight)

by @olvrhhn.bsky.social *, @christophreich.bsky.social *, @neekans.bsky.social, @dcremers.bsky.social, Christian Rupprecht, @stefanroth.bsky.social

🌍: visinf.github.io/cups

Poster: Thursday, 1:30 PM, Poster 19

🌍: visinf.github.io/scenedino/

Talk: Friday, 10:00 AM, Oral Session 5
Poster: Friday, 10:30 AM, Poster 12

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion (ICCV2025)

by @jev-aleks.bsky.social *, @christophreich.bsky.social *, @fwimbauer.bsky.social, @olvrhhn.bsky.social, Christian Rupprecht, @stefanroth.bsky.social, and @dcremers.bsky.social

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