Anton Obukhov @obukhov.ai · 16/12/2025 🌐 Web: hf.co/spaces/prs-e... 📕 Paper: hf.co/papers/2512.... 🐙 Code: github.com/prs-eth/ster... 🤗 Demo: hf.co/spaces/tosha... 🤗 Weights: hf.co/prs-eth/ster... By ETHZ (Tjark, @bingxinke.bsky.social, , Konrad), University of Bologna (Fabio, @mattpoggi.bsky.social), HUAWEI Bayer Lab (@obukhov.ai) 020
Anton Obukhov @obukhov.ai · 16/12/2025Introducing StereoSpace -- our new end-to-end method for turning photos into stereo images without explicit geometry or depth maps. This makes it especially robust with thin structures and transparencies. Try the demo below 294
Anton Obukhov @obukhov.ai · 11/12/2025Other resources: 🌎 Website: huggingface.co/spaces/huawe... 🎓 Paper: arxiv.org/abs/2512.05000 🤗 Model: huggingface.co/huawei-bayer... 🐙 Code: github.com/huawei-bayer... Team: Daniyar Zakarin*, Thiemo Wandel*, Anton Obukhov, Dengxin Dai. *Work done during internships at HUAWEI Bayer Lab 020
Anton Obukhov @obukhov.ai · 11/12/2025Introducing WindowSeat - our new method for removing reflections from photos taken through windows, on planes, in malls, offices, and other glass-filled environments. Try it with your own photos in this demo: huggingface.co/spaces/tosha... 130
Anton Obukhov @obukhov.ai · 15/05/2025Original announcement of Marigold Depth (CVPR 2024 Oral, Best Paper Award Candidate): x.com/AntonObukhov... 110
Anton Obukhov @obukhov.ai · 15/05/2025Team: Bingxin Ke (@bingxinke.bsky.social), Kevin Qu (@kevinqu.bsky.social), Tianfu Wang ( ), Nando Metzger (@nandometzger.bsky.social), Shengyu Huang, Bo Li, Anton Obukhov (@obukhov.ai), Konrad Schindler. We thank @hf.co for their sustained support. 110
Anton Obukhov @obukhov.ai · 15/05/2025A lot of cutting-edge research in related areas comes from ETH Zürich’s PRS lab, led by Prof. Konrad Schindler. Follow the lab for updates: 🐙 github.com/prs-eth 🤗 huggingface.co/prs-eth 🌐 prs.igp.ethz.ch 🎓 Open ETHZ BSc/MSc projects: prs.igp.ethz.ch/education/op... 110
Anton Obukhov @obukhov.ai · 15/05/2025🤗 Demo (Depth): huggingface.co/spaces/prs-e... 🤗 Demo (Normals): huggingface.co/spaces/prs-e... 🤗 Demo (Albedo): huggingface.co/spaces/prs-e... 🤗 Models: huggingface.co/collections/... 110
Anton Obukhov @obukhov.ai · 15/05/2025🌎 Website: marigoldcomputervision.github.io 🧨 Tutorial: huggingface.co/docs/diffuse... 📗 Paper: arxiv.org/abs/2505.09358 🐙 Training code: github.com/prs-eth/Mari... 130
Anton Obukhov @obukhov.ai · 15/05/2025New modalities include surface normals and intrinsic decompositions like albedo, material properties (roughness, metallicity), and lighting decompositions. Marigold proves to be an efficient fine-tuning protocol that generalizes across image analysis tasks. 160
Anton Obukhov @obukhov.ai · 15/05/2025Big Marigold update! Last year, we showed how to turn Stable Diffusion 2 into a SOTA depth estimator with a few synthetic samples and 2–3 days on just 1 GPU. Today's release features: 🏎️ 1-step inference 🔢 New modalities 🫣 High resolution 🧨 Diffusers support 🕹️ New demos 🧶👇 1448
Reposted by Anton ObukhovMatteo Poggi @mattpoggi.bsky.social · 14/05/2025🍸🍸The TRICKY25 challenge: "Monocular Depth from Images of Specular and Transparent Surfaces" is live! 🍸🍸 Hosted at the 3rd TRICKY workshop #ICCV2025, with exciting speakers! @obukhov.ai @taiyasaki.bsky.social Site: sites.google.com/view/iccv25t... Codalab: codalab.lisn.upsaclay.fr/competitions... 011
Anton Obukhov @obukhov.ai · 25/04/2025The workshop report is now released! arxiv.org/abs/2504.17787 121
Anton Obukhov @obukhov.ai · 23/03/2025Huawei Research Center Zürich is looking for a Research Scientist intern to work with me on advancing foundation models for computer vision, focusing on enhancing computational photography features in mobile phones. ˙✧˖°📸⋆｡˚ careers.huaweirc.ch/jobs/5702605...careers.huaweirc.chResearch Intern - Foundation Models for Computer Vision - Huawei Research Center ZürichIf you are enthusiastic in shaping Huawei’s European Research Institute together with a multicultural team of leading researchers, this is the right opportunity for you! 092
Anton Obukhov @obukhov.ai · 14/03/2025Look at them stripes! A principled super-resolution drop by colleagues from PRS-ETH! Interactive demo with gradio-dualvision down in the post 070
Anton Obukhov @obukhov.ai · 04/02/2025MDEC Challenge update! The 4th Monocular Depth Estimation Workshop at #CVPR2025 will be accepting submissions in two phases: 🚀 Dev phase: Feb 1 - Mar 1 🎯 Final phase: Mar 1 - Mar 21 Website: jspenmar.github.io/MDEC/ 🌐 Codalab: codalab.lisn.upsaclay.fr/competitions... Bring your best depth! 274
Anton Obukhov @obukhov.ai · 31/01/2025Update about the 4th Monocular Depth Estimation Workshop at #CVPR2025: 🎉 Website is LIVE: jspenmar.github.io/MDEC/ 🎉 Keynotes: Peter Wonka, Yiyi Liao, and Konrad Schindler 🎉 Challenge updates: new prediction types, baselines & metrics 120
Anton Obukhov @obukhov.ai · 25/01/2025Not finished of course, but it has been demonstrated that such massive compute might be excessive. Video makes sense, but top labs have already delivered astounding video generators with comparable resources. 100
Anton Obukhov @obukhov.ai · 25/01/2025What's the next frontier after LLMs, that will demand nuclear-powered GPU clusters? No agents or AGI please 320
Anton Obukhov @obukhov.ai · 21/12/2024Stay tuned for more updates and resources! MDEC Team: Matteo Poggi (@mattpoggi.bsky.social), Fabio Tosi, Ripudaman Singh Arora, Anton Obukhov (@obukhov.ai), Jaime Spencer, Chris Russell (@cruss.bsky.social), Simon Hadfield, Richard Bowden. 010
Anton Obukhov @obukhov.ai · 21/12/2024The 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. 1223
Reposted by Anton ObukhovNando Metzger @nandometzger.bsky.social · 19/12/2024Monocular 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) 1201
Anton Obukhov @obukhov.ai · 19/12/2024Team ETH Zürich: Massimiliano Viola, Kevin Qu (@kevinqu.bsky.social), Nando Metzger (@nandometzger.bsky.social), Bingxin Ke (@bingxinke.bsky.social), Alexander Becker, Konrad Schindler, and Anton Obukhov (@obukhov.ai). We thank @hf.co and @gradio-hf.bsky.social for their continuous support. 030
Anton Obukhov @obukhov.ai · 19/12/2024🌎 Website: marigolddepthcompletion.github.io 🤗 Demo: huggingface.co/spaces/prs-e... 📕 Paper: arxiv.org/abs/2412.13389 👾 Code: github.com/prs-eth/mari...huggingface.coMarigold Depth Completion - a Hugging Face Space by prs-ethDiscover amazing ML apps made by the community 140
Anton Obukhov @obukhov.ai · 19/12/2024Traditionally, depth completion was framed as image-guided depth interpolation. We leverage Marigold, a diffusion-based monodepth model, to reframe it as sparse-depth-guided depth generation. How the turntables! Check out the paper anyway 👇 130
Anton Obukhov @obukhov.ai · 19/12/2024Depth Completion addresses sparse, incomplete, or noisy measurements from photogrammetry or sensors like LiDAR. Sparse points aren’t just hard for humans to interpret — they also hinder downstream tasks. 130
Anton Obukhov @obukhov.ai · 19/12/2024Introducing ⇆ 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 🧵 2197
Reposted by Anton ObukhovChris Offner @chrisoffner3d.bsky.social · 17/12/2024The most recent fads are "the mind is a like a computer" and now "the mind is like an LLM." 🤷♂️ 011
Reposted by Anton Obukhovlinyijin.bsky.social @linyijin.bsky.social · 13/12/2024Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes. 25912
Reposted by Anton ObukhovJia-Bin Huang @jbhuang0604.bsky.social · 13/12/20243D illusions are fascinating! 🤩 But it takes exceptional artistic skills to make one. We present Illusion3D - a simple method for creating 3D multiview illusions, where the interpretations change depending on your perspectives. Let's play Where's Waldo, shall we? 😆 1143
Anton Obukhov @obukhov.ai · 04/12/2024Interesting! Switzerland continues to build its own Silicon Valley www.wired.com/story/openai...wired.comOpenAI Poaches 3 Top Engineers From DeepMindThe new hires, all experts in computer vision, are the latest AI researchers to jump to a direct competitor in an intensively competitive talent market. 070
Anton Obukhov @obukhov.ai · 02/12/2024The team: Bingxin Ke (@bingxinke.bsky.social), Dominik Narnhofer, Shengyu Huang, Lei Ke, Torben Peters, Katerina Fragkiadaki, Anton Obukhov (@obukhov.ai), and Konrad Schindler. We thank @hf.co for continuous support and @redmond.ai for extra training resources. 030
Anton Obukhov @obukhov.ai · 02/12/2024🌍 Website: rollingdepth.github.io 🤗 Hugging Face Space: huggingface.co/spaces/prs-e... 📕 Paper: arxiv.org/abs/2411.19189 👾 Code: github.com/prs-eth/roll... 120
Anton Obukhov @obukhov.ai · 02/12/2024Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵 1407
Anton Obukhov @obukhov.ai · 30/11/2024At least they are not using legs anymore! Likewise Chris did not use optical illusions. Ethical stress testing 000
Anton Obukhov @obukhov.ai · 29/11/2024Lol, according to this criterion, I am either an AI bro (I can see how one earns that by touching T2I) or an aggro (what is that outside gaming context?). Or a union of all that 130
Anton Obukhov @obukhov.ai · 28/11/2024I still think Hugging Face Posts huggingface.co/posts feature missed the opportunity to (re)consolidate AI scientists community by refusing to go Mobile and making the UI less rigid. But great that it is still happening, regardless of the platformhuggingface.co 230
Reposted by Anton ObukhovChris Offner @chrisoffner3d.bsky.social · 27/11/2024The iPhone LiDAR depth is pretty stable but low-res and low detail. Monodepth is highly detailed but unstable ("depth flickering"). For more stable and detailed metric depth, I solve for the per-frame affine transform that optimally "anchors" the monodepth to the LiDAR. youtube.com/shorts/u3OVj...youtube.comAnchoring monodepth to LiDAR depth | Pedestrian walkYouTube video by Chris Offner 3594
Reposted by Anton ObukhovKris Kashtanova @kris.art · 23/11/2024Good morning! Time to have a coffee ☕️ and update all the AI starter packs 🥹 3101
