Lightnews — Scholar-powered news

Visual Inference Lab @visinf.bsky.social · 9d

🎓 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

5 9

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

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

3

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

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

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

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

1 3

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

🌍: visinf.github.io/scenedino/

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

1 3

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

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

1 3

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

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

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

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

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 Visual Inference Lab

DAGM GCPR 2025 @gcpr-by-dagm.bsky.social · Aug 21

🌟 Keynotes at #GCPR2025 🌟

🎤 Prof. Dima Damen (Uni Bristol & Google DeepMind)

🗓️ Thursday, Sept 25, 2025. 10:30–11:30

Talk:Opportunities in Egocentric Vision

Discover new frontiers in egocentric video understanding, from wearable devices to large-scale datasets.

🔗 www.dagm-gcpr.de/year/2025/re...

4 10

Reposted by Visual Inference Lab

DAGM GCPR 2025 @gcpr-by-dagm.bsky.social · Jul 22

🚨 Nectar Track @ #GCPR2025 — Call for Submissions! 🧠📢

Have a top-tier paper from the last year (CVPR, NeurIPS, ICLR, ECCV, ICCV, etc.)?

Share your work with the vibrant GCPR community!

🗓️ Submission Deadline: July 28, 2025

🔗 Instructions: www.dagm-gcpr.de/year/2025/su...

DAGM GCPR (Submission Instructions)

www.dagm-gcpr.de

1 3 3

Reposted by Visual Inference Lab

Vision and Graphics Trends @si-cv-graphics.bsky.social · Jul 11

𝗙𝗲𝗲𝗱-𝗙𝗼𝗿𝘄𝗮𝗿𝗱 𝗦𝗰𝗲𝗻𝗲𝗗𝗜𝗡𝗢 𝗳𝗼𝗿 𝗨𝗻𝘀𝘂𝗽𝗲𝗿𝘃𝗶𝘀𝗲𝗱 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗦𝗰𝗲𝗻𝗲 𝗖𝗼𝗺𝗽𝗹𝗲𝘁𝗶𝗼𝗻
Aleksandar Jevtić, Christoph Reich, Felix Wimbauer ... Daniel Cremers
arxiv.org/abs/2507.06230
Trending on www.scholar-inbox.com

3 12

Reposted by Visual Inference Lab

Christoph Reich @christophreich.bsky.social · Jul 9

🦖 We present “Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion”. #ICCV2025
🌍: visinf.github.io/scenedino/
📃: arxiv.org/abs/2507.06230
🤗: huggingface.co/spaces/jev-a...
@jev-aleks.bsky.social @fwimbauer.bsky.social @olvrhhn.bsky.social @stefanroth.bsky.social @dcremers.bsky.social

1 10 24

Reposted by Visual Inference Lab

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

Visual Inference Lab @visinf.bsky.social · Jun 20

We presented:

Scene-Centric Unsupervised Panoptic Segmentation (visinf.github.io/cups)

Guided Latent Slot Diffusion for Object-Centric Learning (guided-sa.github.io)

Disentangling Polysemantic Channels in Convolutional Neural Networks (arxiv.org/abs/2504.12939)

6

Visual Inference Lab @visinf.bsky.social · Jun 20

We had a great time at #CVPR2025 in Nashville!

1 2 20

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

Disentangling Polysemantic Channels in Convolutional Neural Networks

by @robinhesse.bsky.social, Jonas Fischer, @simoneschaub.bsky.social, and @stefanroth.bsky.social

Paper: arxiv.org/abs/2504.12939

Talk: Thursday 11:40 AM, Grand ballroom C1
Poster: Thursday, 12:30 PM, ExHall D, Poster 31-60

5

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

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

by Krishnakant Singh, @simoneschaub.bsky.social, and @stefanroth.bsky.social

Project Page: visinf.github.io/glass

Sunday 4:00 PM, ExHall D, Poster 239

1 5

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

Scene-Centric Unsupervised Panoptic Segmentation

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

Sunday, 8:30 AM, ExHall D, Poster 330
Project Page: visinf.github.io/cups

1 2 7

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

We are presenting 3 papers at #CVPR2025!

1 2 7

Reposted by Visual Inference Lab

Christoph Reich @christophreich.bsky.social · Apr 4

Check out the #MCML blog post on our recent #CVPR2025 #highlight paper🔥

Munich Center for Machine Learning @munichcenterml.bsky.social · Apr 3

𝗠𝗖𝗠𝗟 𝗕𝗹𝗼𝗴: Robots & self-driving cars rely on scene understanding, but AI models for understanding these scenes need costly human annotations. Daniel Cremers & his team introduce 🥤🥤 CUPS: a scene-centric unsupervised panoptic segmentation approach to reduce this dependency. 🔗 mcml.ai/news/2025-04...

1 7

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

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

Paper: arxiv.org/abs/2504.01955
Project Page: visinf.github.io/cups
Code: github.com/visinf/cups
MCML Blogpost: mcml.ai/news/2025-04...

1 5

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

✅ Outperform the SotA by a significant margin.
✅ Generalize to different datasets, including an OOD setting.
✅ Stable performance across domains, different from supervised learning.

1 2

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

We train a panoptic network on our high-precision pseudo-labels using self-enhanced copy-paste augmentation. Self-training refines predictions via a momentum network, aligning and filtering augmented outputs into self-labels. 🚀

1 2

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

CUPS consists of pseudo-label generation, network bootstrapping, and self-training. We take inspiration from Gestalt principles (similarity, invariance, & common fate) and generate high-res. panoptic pseudo labels by complementing visual representations with depth & motion cues.

1 2