Vahe Taamazyan
vaheta.bsky.social
Vahe Taamazyan
@vaheta.bsky.social
Helping robots see @ http://intrinsic.ai (Alphabet company). Here talking about 3D Computer Vision and everything around it. Views are my own.
Pretty sure my first words were cv2.imread. or maybe cv::imread, now that I think about it. @opencv.bsky.social @philnelson.bsky.social
June 13, 2025 at 5:19 PM
This has been one of the most exciting and demanding projects I’ve worked on.

Over the past 6 months, we teamed up with OpenCV, the BOP benchmark, and the CIRP Lab @uhmanoa.bsky.social to run a global challenge on 6DoF pose estimation for complex industrial parts. 🧵
June 10, 2025 at 12:25 AM
Want to know if humanoid robots have finally become practical? See if more of them roll smoothly on wheels instead of stumbling around on legs. Until then, they’re stuck in demo mode - not deployment and scaling mode.
April 1, 2025 at 6:38 AM
Gotta admit – I enjoy deleting code way more than writing it.
March 19, 2025 at 4:59 AM
CV/ML paper naming strategies:

- Answering yes to an obvious question? → “Do You Need X for Y?”
- New one-shot model? → “X Anything”
- Overhyping something trivial? → “All You Need Is X”
March 12, 2025 at 8:34 PM
Roses are red,
Violets are blue,
Submissions are open,
We're waiting for you.

A few important updates regarding the Bin Picking Challenge:
opencv.org/blog/importa...
Important Updates: Bin-Picking Challenge Phase 1 Submissions Open & More!
We’re excited to announce several key updates to the Perception Challenge for Bin-Picking aka the Bin-Picking Challenge (BPC)! Phase 1 Submissions Open On February 14th! Get ready to showcase your sol...
opencv.org
February 14, 2025 at 9:16 PM
🚀 Internship Opportunity! 🚀

Our small research team is looking for two talented interns to join us! If you're passionate about cutting-edge research at the intersection of computer vision and robotics, this is your chance to contribute to an exciting, high-impact project.
February 14, 2025 at 3:57 AM
Prediction: There’ll be more people calling themselves software developers in 2–3 years than there are now.
February 6, 2025 at 4:42 PM
I made a bet with a friend on 1 Nvidia stock that in 5 years, I’ll be able to buy a robot that can cook pasta in my kitchen, straight from raw ingredients, with no special setup. Just in case, I’ve already bought the stock😆. What are my chances?
February 5, 2025 at 8:02 PM
The Bin Picking Challenge is live! Detect the 6DoF poses of 10 challenging parts and compete for $60K in prizes. Some of them are quite challenging to detect accurately. The video shows a few of the parts in rotation - are you up for the challenge?
February 5, 2025 at 12:25 AM
The Bin Picking Challenge is now open!
Big news for computer vision enthusiasts! Intrinsic.ai is sponsoring the Bin-Picking Challenge for Perception, with $60,000 in prizes and a chance to present your work at the CVPR Perception for Industrial Robotics Automation Workshop! 🧵 1/5
February 1, 2025 at 8:51 AM
I see people debating the Humanity’s Last Exam dataset. I actually contributed a problem to it. For the past 2 years, I’ve used a much simpler version of that problem to evaluate new LLMs—and they’ve all failed miserably. I can’t speak for other problems, but once an LLM solves mine, I’m retiring 🫡
January 26, 2025 at 11:48 PM
Big news for computer vision enthusiasts! Intrinsic.ai is sponsoring the Bin-Picking Challenge for Perception, with $60,000 in prizes and a chance to present your work at the CVPR Perception for Industrial Robotics Automation Workshop! 🧵 1/5
January 13, 2025 at 11:08 PM
1/ Excited to share that our latest work from Intrinsic will be presented as a paper at SIGGRAPH Asia 2024! 🎉

We’ve developed a plenoptic 3D vision system that addresses a key challenge in industrial robotics: providing robots reliable 3D input data. 🧵⬇️
November 27, 2024 at 12:57 AM
My feelings about humanoid hype
November 25, 2024 at 4:03 PM
This. Also, I’ll be talking a lot more about 6DoF pose in this account in the coming weeks
Submitted a 6D Object Pose Estimation method at CVPR? 📝

Show the world that it actually works in practice and join the BOP challenge. 🦾

7 days left to win the BOP 2024 awards in the model-based and model-free tracks. 🏆
BOP: Benchmark for 6D Object Pose Estimation
bop.felk.cvut.cz
November 22, 2024 at 7:34 PM
1/ A small glimpse into our work at Intrinsic. Building reliable robotics & perception systems is really hard. AI solutions still struggle with hallucinations & occasional failures, which is a major reason why AI isn’t yet widely used in many industries. But that’s changing.
November 22, 2024 at 4:25 AM
You can remove the Discover tab (recommendations) and keep just the Following tab in Bluesky's settings. It’s a simple way to avoid falling down the rabbit hole of emotion-triggering, algorithmic posts. Love this feature!
November 21, 2024 at 8:07 PM
It was taking me forever to find relevant people to follow on twitter. These bluesky starter packs are goated
After my general computer vision starter pack is now full (150/150 entries reached), here is one specific to 3D Vision: go.bsky.app/Cfm9XFe
November 21, 2024 at 5:23 PM
Reposted by Vahe Taamazyan
Starting out the bluesky journey looking for a strong PhD student in 3D Vision!
If you are interested in 3D Vision - specially in using light & camera motion for reconstruction - MVS, SFM, SLAM with Photometric Stereo, and its application in robotics and medical imaging please reach out to me!
November 20, 2024 at 11:14 PM
3D transforms (like mapping one camera’s view to another) can be tricky, even for seasoned pros. I’m diving into the math and intuition behind them for my next blog post. What aspects of 3D transforms have confused you the most? Let me know—I might cover them!
November 20, 2024 at 7:24 PM
Bluesky’s audience is actually impressing me so far—bonus points for the lack of pornbots! Guess I’ll be juggling posts on both Twitter and Bluesky now.
November 20, 2024 at 7:21 PM
Ok, let’s give this app a chance!
November 19, 2024 at 11:17 PM