Happy news! Last week, I successfully defended my PhD thesis (cum laude)😀 Many thanks to my supervisors Gijs Dubbelman and Peter de With, and committee members Bastian Leibe, Cees Snoek, Julian Kooij, and Henk Corporaal! Next: a research visit at RWTH Computer Vision Group.

The Computer Vision Foundation open access proceedings team is proud to announce that the #CVPR2024 proceedings is now online: Main conference: openaccess.thecvf.com/CVPR2024 Workshops: openaccess.thecvf.com/CVPR2024_works… Enjoy and I'll see all of you in Seattle!

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think discuss: huggingface.co/papers/2409.11… Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image

Check out our work on fine-tuning of image-conditional diffusion models for depth and normal estimation. Widely used diffusion models can be improved with single-step inference and task-specific fine-tuning, allowing us to gain better accuracy while being 200x faster!⚡ 🧵(1/6)

Honored to be on this list 😊 Thanks European Conference on Computer Vision #ECCV2026 organizers and ACs! And congrats to the other outstanding reviewers!

The BRAVO Challenge 2014 attracted nearly 100 submissions from international teams representing notable research institutions. The results reveal valuable insights in developing reliable semantic segmentation models. #ECCV2024 #UNCVWorkshop arxiv.org/abs/2409.15107

🚀Check our recent work #Interactive4D to achieve interactive #LiDAR segmentation of multiple objects on multiple scans simultaneously. Work with Ilya Fradlin, Kadir Yılmaz, TheodoraKontogianni, and Bastian Leibe. 🌐Project: ilya-fradlin.github.io/Interactive4D/ 📜Paper: arxiv.org/pdf/2410.08206👇🧵

Image segmentation doesn’t have to be rocket science. 🚀 Why build a rocket engine full of bolted-on subsystems when one elegant unit does the job? 💡 That’s what we did for segmentation. ✅ Meet the Encoder-only Mask Transformer (EoMT): tue-mps.github.io/eomt (CVPR 2025) (1/6)

Very excited about this work!

I'll be presenting "DINO in the Room (DITR)", the winning method of the ScanNet++ 3D semantic segmentation challenge, tomorrow at CVPR at 10 a.m. in Room 211. Project page: visualcomputinginstitute.github.io/DITR/

🚨 CVPR Highlight Alert! 🚨 We’re presenting our Encoder-only Mask Transformer (EoMT) tomorrow at #CVPR2025, 10:30–12:30, Poster #407! 🎸 👉 github.com/tue-mps/eomt ➕ Bonus: we're releasing the biggest EoMT yet… (1/2)

New model alert in Transformers: EoMT! EoMT greatly simplifies the design of ViTs for image segmentation 🙌 Unlike Mask2Former and OneFormer which add complex modules like an adapter, pixel decoder and Transformer decoder on top, EoMT is just a ViT with a set of query tokens ✅

I like the Encoder-only Mask Transformer (EoMT): basically removing all the bells and whistles, and doing panoptic segmentation with an almost vanilla ViT. You're sliiiiightly worse for the same encoder size, but it's a lot simpler/faster and (likely) more scalable. I wish they