Alexey Artemov
@artonson
Followers
664
Following
662
Media
50
Statuses
2K
3D Computer Vision and Machine Learning at Apple . Ex-TUM, ex-Skoltech, ex-Yandex. Notes on 3D Computer Vision, Statistics, Learning, and Software
München, Germany
Joined November 2009
Excited to share the release of Sk3D: a new multi-sensor dataset for multi-view 3D surface reconstruction. Sk3D provides registered RGB **and depth** for 7 sensors of varying resolutions and modalities. #CVPR2023 Project: https://t.co/GRsPnWqjX9 Video: https://t.co/4CxRzlAJm7
0
18
53
Happy to share our latest research on human face 👧🏾👨🏻🦳👳🏾♂️👶🏼 and, importantly, head 💂🏻♀️🧕🏾🧑🚀🧟tracking! DenseMarks delivers dense features for use in multiple tasks - check it out!
❌ Tracking by 68 sparse face landmarks? ✅ Tracking by dense, per-pixel head landmarks 📣 DenseMarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks https://t.co/GBKBUYHaSb 🧵
0
0
9
Excited to share the opportunities for two internships at the Apple European Vision Group. Join us in expanding the boundaries of human-centric vision and generative AI technologies for millions of Apple users https://t.co/PiLsD0FzlX
jobs.apple.com
Apply for a Research Scientist Intern – Human-Centric Generative AI job at Apple. Read about the role and find out if it’s right for you.
3
14
95
Started a new job this week as a 3D Computer Vision and Machine Learning Research Engineer at Apple . Exciting times ahead ;-)
10
6
267
DeepMIF project page: https://t.co/m8DJanWH2T AutoInst project page:
0
0
4
Happy to announce that two our papers "DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping" and "AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans" have been accepted to IROS 2024 Abu Dhabi! Congratulations to the team!
1
0
8
We're looking to fill the secretary position in our lab in Garching at @TU_Muenchen! Wir suchen für unser Team ab sofort in Voll- oder Teilzeit eine Besetzung der Stelle Lehrstuhlsekretärin / Lehrstuhlsekretär (m/w/d) !!! Details / Applications Process: https://t.co/dAuZG9diHo
3
9
21
We achieve higher completion rate and perceptually appealing results by fitting a non-metric monotonic implicit field to LiDAR 3D point clouds, enforcing monotonous constraints over samples along LiDAR rays. Joint work with Kutay Yilmaz, Anastasiia Kornilova, Matthias Nießner.
0
0
4
DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping A method for large-scale 3D scene reconstruction from sparse 3D LiDAR scans. Project: https://t.co/Mh1zj0P9KF Vid: https://t.co/OGITkxikxi Text: https://t.co/N6EzCrBvFA
1
5
21
MeshGPT has been selected as a highlight at #CVPR2024 #Seattle! Let's goo 🚀 (or not depending on the visa situation 🥲)
(1/3) 🚀Excited to share that MeshGPT will be presented at #CVPR24! We show that GPT models can directly generate 3D meshes in an autoregressive fashion without relying on intermediates such as SDFs or density volumes. https://t.co/ynrf0qjYVF
https://t.co/rQe7ipP15t
1
2
59
We leverage multi-modal self-supervised features and perform graph-cuts to generate instance proposals. These initial proposals are further refined with a self-training algorithm. Joint w/ @CedricPerauer, Laurenz Heidrich, Haifan Zhang, @MattNiessner , and Anastasiia Kornilova
0
1
3
AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans A method for unsupervised instance segmentation of 3D outdoor LiDAR scenes. Project: https://t.co/m8DJanWH2T Vid: https://t.co/Z9OyZbskdJ Paper : https://t.co/rrmvQdjmWV
2
6
21
Hit two milestones today: * 1K overall cites of my work https://t.co/BGvohtJt6b * 400 cites for ABC dataset https://t.co/zQaI0RMi7S Very thankful to colleagues and encouraged to keep up the work.
0
0
41
Check out our #CVPR'24 papers on 3D human interactions, generative 3D modeling, and uncertainty-aware and unsupervised 3D semantic scene understanding! Congrats to @craigleili @david_roz_ @chrdiller @yawarnihal @shivangi2201 @jiapeng_tang @AnhQuanCAO for their amazing work!
3
29
118
Our group has fourteen papers accepted at #CVPR'2024! Exciting topics: lots of diffusion & transformers focusing on generative AI for image synthesis, geometry generation, and many more - check it out! I'm so proud of everyone involved - let's go 🚀🚀 https://t.co/rEHOJusF4g
8
61
611
Our priors encode feature-aware fields on surface meshes, enabling to localize and recover sharp geometric feature curves for automatic mesh optimization. Joint work with Natalia Soboleva, Olga Gorbunova, @IvanovaMPe @burnaevevgeny @MattNiessner and Denis Zorin
0
0
3
Sharp Feature Priors for Resolution-Free Surface Remeshing Automatic feature detection and remeshing for arbitrary resolution mesh reconstructions. Project: https://t.co/VbIBmYEi72 Vid: https://t.co/7qUvUD5i48
1
12
47
(1/2) Check out 𝐌𝐞𝐬𝐡𝐆𝐏𝐓! MeshGPT generates triangle meshes by autoregressively sampling from a transformer model that produces tokens from a learned geometric vocabulary. As a result, we obtain clean and compact meshes :) https://t.co/ynrf0qjYVF
https://t.co/rQe7ipP15t
22
422
2K
Join this workshop if you need to: * train large DL models exceeding GPU memory * scale your model training while optimizing compute use * want to learn about real-world use-cases and future vision of all this
Excited to announce our Workshop on Advancing Neural Network Training, WANT @NeurIPSConf!🚀 Save GPU hours, keep accuracy! Join HPC & AI experts on Dec 16, submit papers by Sep 29. #AI #WANT #HPC #NeurIPS2023 #EfficientTraining Details: https://t.co/H5PIxu6xGw
0
1
5
The project is a result of 2-year effort by the team of 16 people at Skoltech and collaborators from multiple orgs. Pushed forward by the incredible Oleg Voynov and the team; co-led by Prof. Denis Zorin, Prof. Dzmitry Tsetserukou, myself, and Prof. Evgeny Burnaev.
0
1
0
Data summary: * 1.4M images of 107 scenes from 100 viewing directions under 14 lighting conditions. * Smartphones, RealSense, Kinect, industrial cameras, and structured-light scanner as reference. * Diverse, challenging materials (specular, reflective, translucent, etc.).
1
1
1