Postdoc @VcaiMpi MPI for Informatics | Virtual Avatars, Human Motion, Physical AI | Prev. PhD @Polytechnique, @Ubisoft @CYENSCoE @la_UPC | Dad 👦🏻👶🏻
Stuttgart, Germany
Joined June 2020
- Tweets328
- Following601
- Followers360
- Likes626
Eduardo Alvarado retweeted
Exactly. My concern isn’t with the authors or how quickly they built on existing work. It’s with the surrounding hype that research can now be done in 2–3 days and that peer review no longer matters. We should celebrate advances without creating misleading expectations for younger researchers.
Eduardo Alvarado retweeted
カメラ映像から皮膚の下の「筋肉の変形」を復元するAI「SOMA」
🔹RGB映像から皮膚・姿勢を観測、筋肉の変形を推定
🔹皮膚・筋肉・骨の多層人体モデルを生成
🔹120台のカメラ＋特殊マーカースーツで「SKIM」を構築
FEMに頼らず、表面観測から解剖学的な人体アニメーションを生成。
情報元はリプ欄。
Eduardo Alvarado retweeted
duardo Alvarado（@roboonaut）氏によるGoogleの3D顔モデル「GNM」とMediaPipeを組み合わせたフェイストラッキングの試作プロジェクト。
GNMヘッドで記録したランドマークと実画像の検出結果を比較し個人差をフィット。
まだ粗いもののリアルな顔追従を実現。
Eduardo Alvarado retweeted
Quantum architecture search (QAS) meets 3D!
Designing expressive, lightweight quantum neural networks (QNNs) that mitigate barren plateaus is hard. Our 𝐿𝑎𝑦𝑒𝑟𝑒𝑑-𝑄𝐴𝑆 discovers such QNNs for point cloud classification.
4dqv.mpi-inf.mpg.de/LQAS/
#3DV2026 #quantum #QeCV #QML
Eduardo Alvarado retweeted
🔥 #3DV2026 Oral: We present a matrix-free Levenberg-Marquardt optimizer that makes second-order optimization practical for 3DGS! 🚀
Eduardo Alvarado retweeted
What a fantastic workshop! 🚀 Huge thanks to our amazing speakers, insightful poster presenters, dedicated reviewers, and the engaged audience who stayed with us throughout the day. We couldn't have asked for a better community! see you next time! 🙌 #CVPR2025 #HumanMotion
Eduardo Alvarado retweeted
Come and talk with us about the future of Human Holoportation. #CVPR25
🧐 A novel end-to-end real-time method.
🫡 Faster speed and higher accuracy.
Main Conf:
June 13 10:30~12:30 | Poster-37 | ExHall D
Also 3D Human Workshop:
June 12 15:00~16:30 | Poster-324 | ExHall D
Eduardo Alvarado retweeted
Excited to present BimArt at #CVPR2025🎉
June 11
• Spotlight talk@Humanoid Agents (10:30–11:00, Room 101D)
• Poster (ExHallD #127): 15:00–15:30
June 12
• Poster@3D Human Understanding (ExHallD #323) 15:30–16:30
June 15
• Main Conf Poster (ExHallD#146) 17:00–19:00
Eduardo Alvarado retweeted
Looking forward to #CVPR 2025 🚀!
Want to chat? Drop me a message or an email!
We will present some cool works in the areas of human rendering and capture, general object reconstruction, and hand motion synthesis.
Interested? More details below 🧵.
Eduardo Alvarado retweeted
Announcing our new partnership with @BostonDynamics! We're teaming up to advance humanoid robotics through reinforcement learning.
Learn more — rai-inst.com/resources/press…
Eduardo Alvarado retweeted
Ever wondered how a SINGLE token represents all subject regions in personalization? Many methods use this token in cross-attention, meaning all semantic parts share the same single attention value. We present Nested Attention, a mechanism that generates localized attention values
Eduardo Alvarado retweeted
𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗼𝘀𝘁𝗲𝗿𝘀 at the 2nd Workshop on Quantum Computer Vision and Machine Learning (QCVML) at #ECCV2024: qcvml.github.io/#posters
• The 𝙙𝙚𝙖𝙙𝙡𝙞𝙣𝙚 is 15.09.24, 23:59 AOE. Please use the supplied template.
• QCVML workshop day and time: 29.09.24, 1 pm CEST.
Eduardo Alvarado retweeted
Submit your work to the #ISMAR2024 Workshop on Privacy-Aware Human State Estimation for #MR/#VR! The focus is on data less likely to lead to person identification in the human pose, mesh and eye gaze estimation (e.g., events or acoustic signals).
Details: sites.google.com/keio.jp/ism…
Eduardo Alvarado retweeted
Code and data is available here vcai.mpi-inf.mpg.de/projects… !
Happy to present Holoported Characters, which is accepted at #CVPR2024 :)
Let our virtual avatar explain our method to you (sound on).
Big thanks to my colleagues: Ashwath, @DiogoLuvizon, Guoxing, @VGolyanik, and Christian
Eduardo Alvarado retweeted
You need one if you wake up every day excited about new ideas that you just have to pursue. If you are happy working on other people’s ideas you don’t need a PhD. If you aren’t happy unless you are pursuing your own ideas, a PhD is a good idea. Not the only path of course.
Eduardo Alvarado retweeted
The HuMoGen @CVPR deadline is in 6 days🙀🙀🙀 We invite you to submit your #MOTION papers!
More details @ humogen.github.io
Eduardo Alvarado retweeted
Sora is our first video generation model - it can create HD videos up to 1 min long. AGI will be able to simulate the physical world, and Sora is a key step in that direction. thrilled to have worked on this with @billpeeb at @openai for the past year openai.com/sora
Eduardo Alvarado retweeted
The submission portal is now open! Looking forward to exciting new works on motion synthesis. @humogen11384
More details on humogen.github.io/
We invite you to submit your Motion Generation papers to the HuMoGen @CVPR workshop!
The deadline is on March 19
More details @ humogen.github.io