Computer Vision Researcher at @RealityLabs. Previously at @Scape. Previous PhD student and Post-Doc at @UniofOxford

London, England
Joined December 2009
Duncan Frost retweeted
Sonata: Advancing Self-Supervised Learning for 3D Point Representations Sonata represents a significant leap forward in the field of 3D self-supervised learning. By identifying and addressing the geometric shortcut and introducing a flexible, efficient framework, it’s an exceptionally robust 3D point representation. This work advances the state of the art and sets the stage for future innovations in 3D perception and its applications. Learn more ➡️ projectaria.com/news/introdu…
11
21
1
70
19,765
Duncan Frost retweeted
📢Sonata: Self-Supervised Learning of Reliable Point Representations📢 Meet Sonata, our"3D-DINO" pre-trained with Point Transformer V3, accepted at #CVPR2025! 🌍: xywu.me/sonata 📦: github.com/facebookresearch/… 🚀: github.com/Pointcept/Pointce… 🔹Semantic-aware and spatial reasoning representations learned with no label; 🔹3x linear probing accuracy (from 21.8% to 72.5%) on ScanNet; 🔹2x data efficiency performance with only 1% of the data compared to previous approaches; 🔹As always, establish new SOTA results across indoor and outdoor 3D perception tasks. Our author team: @HengshuangZhao, @jstraub6, @rapideRobot, @ddetone, @NinjaDuncan, @TianweiS, @Christopher_Xie, @NanYang719.
3
49
6
188
30,619
Duncan Frost retweeted
🚀EgoLifter is open-sourced: github.com/facebookresearch/…! It includes: 🕶️Full recipe for Project Aria datasets, from downloading, pre-processing, to vignette handling 🌟Rewritten 3DGS train/test pipelines using lightning and gsplat 🌐Web-based 3DGS visualizer powered by viser
🚀 Thrilled to introduce EgoLifter, my work on egocentric 3D perception at Meta Reality Labs! EgoLifter incorporates open-world segmentation into 3D Gaussian models, enabling 3D reconstruction and extraction of objects we see in our everyday lives! 🌐
22
2
145
14,460
Duncan Frost retweeted
📹 On several large-scale egocentric video datasets, EgoLifter also showcases the ability to learn consistent 3D features and decompose a 3D scene into 3D object instances, which opens up promising directions for egocentric video understanding in AR/VR applications. 🕶️
1
1
1
6
551
📢 Today, our team is excited to announce 𝑺𝒄𝒆𝒏𝒆𝑺𝒄𝒓𝒊𝒑𝒕: an end-to-end method for scene reconstruction from @RealityLabs Research, which enables AI agents to understand and describe 3D spaces. projectaria.com/scenescript /🧵
6
43
10
270
38,604
Are you interested in 3D scene understanding and reconstruction? Does the challenge of tackling these problems using egocentric image data sound exciting to you?
1
1
71
Our team at Meta Reality Labs Research is looking for PhD candidates with experience in 3D computer vision and machine learning to join us for our Summer 2024 internship program.
1
1
3
270
Often AI methods justify their design by "That's how human's do it". Not always a good idea: 1) we don't fully understand humans. 2) Think about how bad humans are doing basic arithmetic operations like addition or subtraction, and how well computers can do it in comparison.
3
3
30
The main idea of Machine Learning is that everything is simply learned from data instead of tedious handcrafting features. The irony is that we are now doing more empirical research than ever, spending most of our time with data engineering and hyper parameter tuning.
11
68
5
544
Docker containers are kind of neat. They are also kind of a craven surrender to the rotting mess of excessive software complexity.
69
444
58
3,605
Congratulations to NASA and all their collaborators! First powered autonomous flight on another planet successful! Btw, it is also a vision-based flight (single-camera + IMU + laser altimeter).
You wouldn’t believe what I just saw. More images and video to come... #MarsHelicopter go.nasa.gov/ingenuity
1
14
103
Duncan Frost retweeted
NHS staff are being stretched as thin as they possibly can before they break. We had 38,000 vacancies for nurses and 10,000 for doctors even before the pandemic. We must look after our staff now or risk losing them when the dust settles. RT if you agree. ft.com/content/b466d0d3-45f4…
15
681
14
840
Argentina, South Africa, Brazil, and Turkey — all countries that hosted vaccine trials — will have to be satisfied with Pfizer’s gratitude, because (like most countries in the world) they won’t be receiving enough of the vaccine to inoculate their populations anytime soon.
245
2,304
672
3,651
GPT-3 is AGI
In 5 words or less, start a fight without politics
7
5
1
108
Duncan Frost retweeted
This is dum At least an adult has a chance to overcome poverty and social class. A kid has zero chance. This is basically a "most privileged kid of the year" I imagine if I was judged by my life at 15. Broken home, failing in school. Forbes 15 under 15 coming next 🤮
Introducing the first-ever Kid of the Year, Gitanjali Rao ti.me/36xydjU
6
5
57
Pay everyone $1500 to get vaccine It is a stimulus check & big vaccine incentive rolled into one Result: more people get vaccine, it saves lives, helps people financially, and the $400 B pays for itself w/ economic boost from ending pandemic RT if you agree #vaccinestimulus
2,124
9,697
4,395
49,387
So we’re slowly approaching tier 4 lockdown! By the time of Christmas 🎄 we’ll be in Tier 12 which means everyone will have to self isolate from within! You will not be allowed to look in the mirror or talk to yourself. Tier 12 is when you let your soul free.
55
1,277
163
6,240
Replying to @seanmcarroll
@seanmcarroll as an avid listener of the podcast, I was curious if you’re open to suggestions for future interviewees? There are a couple I’d really love to hear you speak with, in particular this mathematical physicist at Lund portal.research.lu.se/portal…
2
1
The 'AR-Cloud' will change the way we view the physical environment. Check out this world-scale AR scene, powered by @Scape
19
145
34
482