Oliver Hahn
@olvrhhn.bsky.social
ELLIS PhD Student w/ @stefanroth.bsky.social and @lealtaixe.bsky.social More: olvrhhn.github.io
Come see INSID3, in-context segmentation with DINOv3, at 2:00 PM in oral session 4D and later at poster #19. #CVPR2026
Gabriele Trivigno@gabtriv.bsky.social · 5mo ago🔥 Can in-context segmentation emerge directly from frozen DINOv3 features? At #CVPR2026, we present INSID3: Training-Free In-Context Segmentation with DINOv3 — a collaboration between PoliTo, TU Darmstadt and TU Munich. Check it out: github.com/visinf/INSID3
📢 [CVPR’26] Can we learn to detect, segment, and track every object in a video without human supervision? Yes, we introduce VideoCUPS, the first unsupervised video panoptic segmentation (VPS) method: 1. Get pseudo-labels from monocular videos. 2. Train a VPS model on them.
🔥 Can in-context segmentation emerge directly from frozen DINOv3 features? At #CVPR2026, we present INSID3: Training-Free In-Context Segmentation with DINOv3 — a collaboration between PoliTo, TU Darmstadt and TU Munich. Check it out: github.com/visinf/INSID3
📢 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.
@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...
career.tu-darmstadt.de
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
📢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.
🎓 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
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! 🇦🇹🏔️
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
🦖 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
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
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
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! ⬇️
🚀Excited to announce our CVPR 2025 paper: Unbiasing through Textual Descriptions! We release new descriptions for 1.9M(!) videos and object-debiased splits for 12 datasets! 🔗Project: utd-project.github.io by @ninashv.bsky.social et al 🧵👇 @cvprconference.bsky.social
UTD Dataset: Mitigating Representation Bias in Video Benchmarks
A dataset with textual descriptions and debiased splits for video benchmarks.
utd-project.github.io
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/
🚀 Never miss a beat in science again! 📬 Scholar Inbox is your personal assistant for staying up to date with your literature. It includes: visual summaries, collections, search and a conference planner. Check out our white paper: arxiv.org/abs/2504.08385 #OpenScience #AI #RecommenderSystems
Excited to share our #CVPR2025 highlight on unsupervised panoptic segmentation!
Visual Inference Lab@visinf.bsky.social · last yr.📢 #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
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
🏔️⛷️ Looking back on a fantastic week full of talks, research discussions, and skiing in the Austrian mountains!
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.
