Lightnews — Scholar-powered news

Reposted by Christoph Reich

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

Reposted by Christoph Reich

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

Christoph Reich @christophreich.bsky.social · Jul 24

Check out our blog post about SceneDINO 🦖
For more details, check out our project page, 🤗 demo, and the hashtag #ICCV2025 paper 🚀

🌍Project page: visinf.github.io/scenedino/
🤗Demo: visinf.github.io/scenedino/
📄Paper: arxiv.org/abs/2507.06230
@jev-aleks.bsky.social

1 2

Reposted by Christoph Reich

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 Christoph Reich

Linus Härenstam-Nielsen @linushn.bsky.social · Jul 9

The code for our #CVPR2025 paper, PRaDA: Projective Radial Distortion Averaging, is now out!

Turns out distortion calibration from multiview 2D correspondences can be fully decoupled from 3D reconstruction, greatly simplifying the problem

arxiv.org/abs/2504.16499
github.com/DaniilSinits...

1 5 12

Christoph Reich @christophreich.bsky.social · Jul 9

🌍Project Page: visinf.github.io/scenedino/
📃Paper: arxiv.org/abs/2507.06230
💻Code: github.com/tum-vision/s...
🤗Demo: huggingface.co/spaces/jev-a...

SceneDINO

Feed-forward SceneDINO: Single input image -> 3D geometry and features -> unsupervised semantics (SSC).

visinf.github.io

4

Christoph Reich @christophreich.bsky.social · Jul 9

Work by: @jev-aleks.bsky.social*, @christophreich.bsky.social*, @olvrhhn.bsky.social, Christian Rupprecht, @stefanroth.bsky.social, and @dcremers.bsky.social @ TUM CVG, @visinf.bsky.social, @munichcenterml.bsky.social, @zuseschooleliza.bsky.social, and @hessianai.bsky.social

1 3

Christoph Reich @christophreich.bsky.social · Jul 9

✅ SceneDINO offers refined, high-resolution, and multi-view consistent (rendered) 2D features.

1 3

Christoph Reich @christophreich.bsky.social · Jul 9

✅SceneDINO outperforms our unsupervised baseline (S4C + STEGO) in unsupervised SSC accuracy.
✅Linear probing our feature field leads to an SSC accuracy on par with 2D supervised S4C.

1 3

Christoph Reich @christophreich.bsky.social · Jul 9

⚗️Distilling and clustering SceneDINO's feature field in 3D results in unsupervised semantic scene completion predictions.

1 3

Christoph Reich @christophreich.bsky.social · Jul 9

🏋SceneDINO is trained to estimate an expressive 3D feature field using multi-view self-supervision and 2D DINO features.

1 3

Christoph Reich @christophreich.bsky.social · Jul 9

🚀 SceneDINO is unsupervised and infers 3D geometry and features from a single image in a feed-forward manner. Distilling and clustering SceneDINO's 3D feature field lead to unsupervised semantic scene completion predictions.

1 4

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 Christoph Reich

arxiv cs.CV @arxiv-cs-cv.bsky.social · Jul 9

Aleksandar Jevti\'c, Christoph Reich, Felix Wimbauer, Oliver Hahn, Christian Rupprecht, Stefan Roth, Daniel Cremers
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
https://arxiv.org/abs/2507.06230

1 2

Reposted by Christoph Reich

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 Christoph Reich

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

We had a great time at #CVPR2025 in Nashville!

1 2 20

Reposted by Christoph Reich

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

Reposted by Christoph Reich

Dominik Schnaus @schnaus.bsky.social · Jun 3

Can we match vision and language representations without any supervision or paired data?

Surprisingly, yes!

Our #CVPR2025 paper with @neekans.bsky.social and @dcremers.bsky.social shows that the pairwise distances in both modalities are often enough to find correspondences.

⬇️ 1/4

1 12 27

Reposted by Christoph Reich

Felix Wimbauer @fwimbauer.bsky.social · May 13

Can you train a model for pose estimation directly on casual videos without supervision?

Turns out you can!

In our #CVPR2025 paper AnyCam, we directly train on YouTube videos and achieve SOTA results by using an uncertainty-based flow loss and monocular priors!

⬇️

1 10 25

Reposted by Christoph Reich

Felix Wimbauer @fwimbauer.bsky.social · Apr 23

Check out our latest recent #CVPR2025 paper AnyCam, a fast method for pose estimation in casual videos!

1️⃣ Can be directly trained on casual videos without the need for 3D annotation.
2️⃣ Based around a feed-forward transformer and light-weight refinement.

Code and more info: ⏩ fwmb.github.io/anycam/

1 6 23

Christoph Reich @christophreich.bsky.social · Apr 4

Check out our recent #CVPR2025 #highlight paper on unsupervised panoptic segmentation🚀
🌍 visinf.github.io/cups/

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

8

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

Christoph Reich @christophreich.bsky.social · Mar 28

Nice one! Have you tried instance segmentation?

1

Christoph Reich @christophreich.bsky.social · Mar 13

Check out the recent CVG papers at #CVPR2025, including our (@olvrhhn.bsky.social, @neekans.bsky.social, @dcremers.bsky.social, Christian Rupprecht, and @stefanroth.bsky.social) work on unsupervised panoptic segmentation. The paper will soon be available on arXiv. 🚀

Daniel Cremers @dcremers.bsky.social · Mar 13

We are thrilled to have 12 papers accepted to #CVPR2025. Thanks to all our students and collaborators for this great achievement!
For more details check out cvg.cit.tum.de

2 6

Reposted by Christoph Reich

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