Zubair Irshad
@zubair-irshad.bsky.social
Research Scientist @Toyota Research Institute | Prev. PhD in AI, ML and CV @GeorgiaTech | Researching 3D Perception, Generative AI for Robotics and Multimodal AI
W: https://zubairirshad.com
W: https://zubairirshad.com
Pinned
Zubair Irshad
@zubair-irshad.bsky.social
· Apr 23
Introducing ✨Posed DROID✨, results of our efforts at automatic post-hoc calibration of a large-scale robotics manipulation dataset.
Try it out at: droid-dataset.github.io
Learn more at:
🌐 arXiv: arxiv.org/pdf/2403.12945
📄 Blog: medium.com/p/4ddfc45361d3
🧵 1/n
Try it out at: droid-dataset.github.io
Learn more at:
🌐 arXiv: arxiv.org/pdf/2403.12945
📄 Blog: medium.com/p/4ddfc45361d3
🧵 1/n
Reposted by Zubair Irshad
FastMap: Revisiting Dense and Scalable Structure from Motion
Jiahao Li, Haochen Wang, @zubair-irshad.bsky.social, @ivasl.bsky.social, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich
tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation
arxiv.org/abs/2505.04612
Jiahao Li, Haochen Wang, @zubair-irshad.bsky.social, @ivasl.bsky.social, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich
tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation
arxiv.org/abs/2505.04612
May 8, 2025 at 12:51 PM
FastMap: Revisiting Dense and Scalable Structure from Motion
Jiahao Li, Haochen Wang, @zubair-irshad.bsky.social, @ivasl.bsky.social, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich
tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation
arxiv.org/abs/2505.04612
Jiahao Li, Haochen Wang, @zubair-irshad.bsky.social, @ivasl.bsky.social, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich
tl;dr: replace BA with epipolar error+IRLS; fully PyTorch implementation
arxiv.org/abs/2505.04612
Introducing ✨Posed DROID✨, results of our efforts at automatic post-hoc calibration of a large-scale robotics manipulation dataset.
Try it out at: droid-dataset.github.io
Learn more at:
🌐 arXiv: arxiv.org/pdf/2403.12945
📄 Blog: medium.com/p/4ddfc45361d3
🧵 1/n
Try it out at: droid-dataset.github.io
Learn more at:
🌐 arXiv: arxiv.org/pdf/2403.12945
📄 Blog: medium.com/p/4ddfc45361d3
🧵 1/n
April 23, 2025 at 11:50 PM
Introducing ✨Posed DROID✨, results of our efforts at automatic post-hoc calibration of a large-scale robotics manipulation dataset.
Try it out at: droid-dataset.github.io
Learn more at:
🌐 arXiv: arxiv.org/pdf/2403.12945
📄 Blog: medium.com/p/4ddfc45361d3
🧵 1/n
Try it out at: droid-dataset.github.io
Learn more at:
🌐 arXiv: arxiv.org/pdf/2403.12945
📄 Blog: medium.com/p/4ddfc45361d3
🧵 1/n
🚀Exciting News! Join us at the inaugural #CVPR2025 Workshop on 3D Vision Language Models (VLMs) for Robotics Manipulation on June 11, 2025, in Nashville, TN! 🦾
robo-3dvlms.github.io
1/N
@cvprconference.bsky.social
robo-3dvlms.github.io
1/N
@cvprconference.bsky.social
February 10, 2025 at 5:01 PM
🚀Exciting News! Join us at the inaugural #CVPR2025 Workshop on 3D Vision Language Models (VLMs) for Robotics Manipulation on June 11, 2025, in Nashville, TN! 🦾
robo-3dvlms.github.io
1/N
@cvprconference.bsky.social
robo-3dvlms.github.io
1/N
@cvprconference.bsky.social
Congrats on the release, demos look cool and it's open source 👏
I'd like to introduce what I've been working at @hellorobot.bsky.social: Stretch AI, a set of open-source tools for language-guided autonomy, exploration, navigation, and learning from demonstration.
Check it out: github.com/hello-robot/...
Thread ->
Check it out: github.com/hello-robot/...
Thread ->
December 4, 2024 at 8:51 AM
Congrats on the release, demos look cool and it's open source 👏
Reposted by Zubair Irshad
In a world full of AI, authenticity will be the most valuable thing in the universe.
November 30, 2024 at 2:39 AM
In a world full of AI, authenticity will be the most valuable thing in the universe.
Reposted by Zubair Irshad
For my first post on Bluesky, this recent talk I did at the recent BMVA one day meeting on World Models is a good summary of my work on Computer Vision, Robotics and SLAM, and my thoughts on a bigger picture of #SpatialAI.
youtu.be/NLnPG95vNhQ?...
youtu.be/NLnPG95vNhQ?...
1 Andrew Davison, Imperial College London - BMVA Symposium: Robotics Foundation & World Models
YouTube video by BMVA: British Machine Vision Association
youtu.be
November 28, 2024 at 2:22 PM
For my first post on Bluesky, this recent talk I did at the recent BMVA one day meeting on World Models is a good summary of my work on Computer Vision, Robotics and SLAM, and my thoughts on a bigger picture of #SpatialAI.
youtu.be/NLnPG95vNhQ?...
youtu.be/NLnPG95vNhQ?...
Reposted by Zubair Irshad
November 27, 2024 at 2:54 AM
Reposted by Zubair Irshad
We are in the process of editing a SLAM handbook, to be published by Cambridge University Press, with many *stellar* contributors. Part 1 is available as an online draft for public comments. Help us find bugs/problems!
Link to release repo is here: lnkd.in/gZhTkaxb
Link to release repo is here: lnkd.in/gZhTkaxb
GitHub - SLAM-Handbook-contributors/slam-handbook-public-release: Release repo for our SLAM Handbook
Release repo for our SLAM Handbook. Contribute to SLAM-Handbook-contributors/slam-handbook-public-release development by creating an account on GitHub.
lnkd.in
November 16, 2024 at 3:45 PM
We are in the process of editing a SLAM handbook, to be published by Cambridge University Press, with many *stellar* contributors. Part 1 is available as an online draft for public comments. Help us find bugs/problems!
Link to release repo is here: lnkd.in/gZhTkaxb
Link to release repo is here: lnkd.in/gZhTkaxb
It's a great tool created by Andreas Geiger and co. (not here yet). Among many other things, I really like the daily digest email it sents out every evening, also you could upvote certain papers to tune the algorithm to your preference better.
November 25, 2024 at 2:43 AM
It's a great tool created by Andreas Geiger and co. (not here yet). Among many other things, I really like the daily digest email it sents out every evening, also you could upvote certain papers to tune the algorithm to your preference better.
Reposted by Zubair Irshad
Here is a list of ML OSS & Open Source / Science enthusiasts I found on Bluesky 🦋
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
November 21, 2024 at 5:19 AM
Here is a list of ML OSS & Open Source / Science enthusiasts I found on Bluesky 🦋
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
Reposted by Zubair Irshad
November 19, 2024 at 11:00 PM
A list and feed to catch up on the latest and greatest happening in AI through research papers, blogs or opinionated thoughts 🦾
Missed you or someone else? Let me know, Feedback/suggestions welcome.
bsky.app/profile/did:...
Missed you or someone else? Let me know, Feedback/suggestions welcome.
bsky.app/profile/did:...
November 22, 2024 at 10:26 PM
A list and feed to catch up on the latest and greatest happening in AI through research papers, blogs or opinionated thoughts 🦾
Missed you or someone else? Let me know, Feedback/suggestions welcome.
bsky.app/profile/did:...
Missed you or someone else? Let me know, Feedback/suggestions welcome.
bsky.app/profile/did:...
Reposted by Zubair Irshad
Lots of advancements in using implicit representations for robotics! Check out this survey.
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
Neural Fields in Robotics: A Survey
Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D d...
arxiv.org
November 18, 2024 at 9:29 PM
Lots of advancements in using implicit representations for robotics! Check out this survey.
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
AI Papers and Educators
November 22, 2024 at 10:12 PM
AI Papers and Educators
Reposted by Zubair Irshad
Great list
Created a #robotics and #vision starter pack. Feel free to suggest yourself or others missing from the list!
go.bsky.app/HcQYMj
go.bsky.app/HcQYMj
November 22, 2024 at 4:21 PM
Great list
Reposted by Zubair Irshad
applying leanrl tricks to maniskill helped solve a cube picking task in a minute with gpu sim (best time was about 40 seconds)
November 22, 2024 at 7:18 AM
applying leanrl tricks to maniskill helped solve a cube picking task in a minute with gpu sim (best time was about 40 seconds)
Reposted by Zubair Irshad
Full CoRL conference recording: www.youtube.com/watch?v=0joZ...
Someone remind me to watch this later
Someone remind me to watch this later
CoRL 2024 Day 1 9:00-10:30
YouTube video by Conference on Robot Learning
www.youtube.com
November 20, 2024 at 10:49 PM
Full CoRL conference recording: www.youtube.com/watch?v=0joZ...
Someone remind me to watch this later
Someone remind me to watch this later
Reposted by Zubair Irshad
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
November 22, 2024 at 1:33 AM
NeurIPS Conference is now Live on Bluesky!
-NeurIPS2024 Communication Chairs
-NeurIPS2024 Communication Chairs
Reposted by Zubair Irshad
November 20, 2024 at 1:54 AM
Reposted by Zubair Irshad
Future Bsky homes for our #computervision conferences!
@cvprconference.bsky.social
@iccv.bsky.social
@eccv.bsky.social
@wacvconference.bsky.social
Stay tuned!
@cvprconference.bsky.social
@iccv.bsky.social
@eccv.bsky.social
@wacvconference.bsky.social
Stay tuned!
November 19, 2024 at 2:05 PM
Future Bsky homes for our #computervision conferences!
@cvprconference.bsky.social
@iccv.bsky.social
@eccv.bsky.social
@wacvconference.bsky.social
Stay tuned!
@cvprconference.bsky.social
@iccv.bsky.social
@eccv.bsky.social
@wacvconference.bsky.social
Stay tuned!
Reposted by Zubair Irshad
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 8:15 AM
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
Created a #robotics and #vision starter pack. Feel free to suggest yourself or others missing from the list!
go.bsky.app/HcQYMj
go.bsky.app/HcQYMj
November 21, 2024 at 1:53 PM
Created a #robotics and #vision starter pack. Feel free to suggest yourself or others missing from the list!
go.bsky.app/HcQYMj
go.bsky.app/HcQYMj
How do we represent 3D world knowledge for spatial intelligence in next-generation robots? We recently wrote an extensive survey paper on this emerging topic, covering recent state-of-the-art! 🦾 🚀
Check it out below. Feedback/Suggestions welcome!
📖arXiv: arxiv.org/abs/2410.20220
Check it out below. Feedback/Suggestions welcome!
📖arXiv: arxiv.org/abs/2410.20220
November 21, 2024 at 1:32 PM
How do we represent 3D world knowledge for spatial intelligence in next-generation robots? We recently wrote an extensive survey paper on this emerging topic, covering recent state-of-the-art! 🦾 🚀
Check it out below. Feedback/Suggestions welcome!
📖arXiv: arxiv.org/abs/2410.20220
Check it out below. Feedback/Suggestions welcome!
📖arXiv: arxiv.org/abs/2410.20220