Profile avatar
nandometzger.bsky.social
PhD @ ETH Zurich | Computer Vision | Monocular Depth | 3D Stuff | Ex intern at Meta nandometzger.github.io
24 posts 1,301 followers 218 following
Regular Contributor
Conversation Starter

I will be giving a talk on open-vocabulary 3D scene understanding at the next ZurichCV meetup! 🗓️ Date: Thursday, January 23rd 18:00 CET 📍Location: @ETH_AI_Center, please see zurichai.ch/events/zurichcv-7 for additional details!

Scaniverse by Niantic is very nice😃 Merry Christmas🎄

The 4th Monocular Depth Estimation Challenge (MDEC) is coming to #CVPR2025, and I’m excited to join the org team! After 2024’s breakthroughs in monodepth driven by generative model advances in transformers and diffusion, this year's focus is on OOD generalization and evaluation.

Monocular depth meets depth completion🚀 Check out our latest work where we modified Marigold to a zero-shot depth completion tool. Everything without retraining🌼 (This paper, for once, contains geese instead of cats😄 keep an eye open)

Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵

I mean I see the suitability of using gated RNNs for refinement (like in RAFT, IronDepth and recently MegaSaM). But it bugs my mind that we are using tools that were initially designed for time series. Aren't there any better design choices?

Ok, i am lowering my standards: does anybody know *any* Perspectives-n-Point implementation in python?

Is there a good python (preferably pytorch) implementation of EPnP? link.springer.com/article/10.1...

Awesome work by @bingxinke.bsky.social

Check out my GenAI starter pack! go.bsky.app/BT1bRvZ

ZurichCV#6 happens tomorrow with Dániel Baráth from the ETH AI Center and and Peter Karkus from NVIDIA. www.zurichai.ch/events/zuric...