Anton Obukhov
@AntonObukhov1
Followers
2K
Following
3K
Statuses
709
Research Scientist in Computer Vision and Generative AI
Zurich
Joined May 2020
Introducing Marigold 🌼 - a universal monocular depth estimator, delivering incredibly sharp predictions in the wild! Based on Stable Diffusion, it is trained with synthetic depth data only and excels in zero-shot adaptation to real-world imagery. Check it out: 🌐 Website: 🤗 Hugging Face Space: 📄 Paper: 👾 Code: The team: Bingxin Ke (@KBingxin), yours truly (@AntonObukhov1), Shengyu Huang (@ShengyHuang), Nando Metzger (@NandoMetzger), Rodrigo Caye Daudt (@rcdaudt), and Konrad Schindler. #ComputerVision #PRS #ETHZurich
48
277
1K
Previous posts:
Update about the 4th Monocular Depth Estimation Workshop at #CVPR2025: 🎉 Website is LIVE! (link below) 🎉 Keynotes: Peter Wonka (@peter_wonka), Yiyi Liao (@yiyi_liao_), and Konrad Schindler 🎉 Challenge updates: new prediction types, baselines & metrics
0
0
0
@tunguz Soon everyone will be asking AI to produce messy illogical typo-ridden limited vocabulary messages
0
0
1
Announcement:
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.
0
0
1
RT @DinoFuzi: 📢 Our paper CubeDiff has been accepted to ICLR 2025! 🎉🎉🎉 CubeDiff achieves SOTA panorama generation with only minimal archit…
0
21
0
RT @DBahdanau: Hiding o1 chain-of-thoughts was very arrogant and condescending. Time to pay for bad decisions.
0
2
0
RT @CSProfKGD: With #CVPR2025 rebuttal week upon us, this is your periodic reminder to check out @deviparikh @DhruvBatraDB @stefmlee GREAT…
0
13
0
What's the next frontier after LLMs, that will demand nuclear-powered GPU clusters? No agents or AGI please
0
0
1
RT @taiyasaki: @ylecun Indeed, we need to burn through the interesting research problems even faster. Three months from idea to final resul…
0
1
0