@makezur

PhD student at Dyson Robotics Lab @ Imperial College London

 London, UK
Joined May 2020
  • Tweets51
  • Following425
  • Followers687
15Media
AgentSTAR is an agentic method for both reconstruction and tracking of articulated objects from monocular videos. We can now track through rapid motion, severe occlusion and thin objects! 

There’s no spoon but we can still track it 🥄
10
45
9
430
79,179
Wrote done my thoughts on what's fundamentally new for vision when using agents --- obviously, apart from some hard problems that have now been nearly solved :)

Agentic Optimisation

Article · @makezur
1
9
1
55
8,788
Christopher Fraser@RealCFraserSep 15
I wonder if something like this could be used for Star Wars fan films to track 3d lightsabers instead of using roto🤔
1
18
1,235
I particularly like this example, where we show our reconstruction alongside the ground-truth hand poses -- it gives a much better sense of the 3D tracking accuracy
1
2
508
For more visuals and details check out our project page, paper and code release! Real2Sim for dynamic scenes is definitely within reach now joint w/ @n_karaev Matthew Chang @JitendraMalikCV @notmahi Project page: agenticstar.github.io Code: github.com/makezur/agenticST…

AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos

AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos. Project page.

agenticstar.github.io
1
2
25
2,386
In my mind, this line of thinking was popularised by Real2Code and SceneScript, but can now finally be taken to the extreme, where code is not only the representation but also what gets the tracking done
15
1,836
Kirill Mazur retweeted
Nicholas Fry@deepfry_nSep 7
I'll be presenting our work at #ECCV2026 in Malmö! 🇸🇪 Find me at the poster and demo sessions: Poster 📅 Thu 10 Sep, 10:30 📍 ExHall #272 Demo 📅 Sat 12 Sep, 8:00 📍 ExHall Also at NeuSLAM Workshop 🤖: Tue 8 Sep, 14:00, Malmö Arena Hotel
Nicholas Fry@deepfry_nJun 1
(1/3) I am happy to share our work on Triangle Splatting SLAM! We show the first RGB-D SLAM to use differentiable triangles as a 3D map representation. Our method enables online mesh-based deformations and collision checking via on-the-fly Delaunay triangulation.
4
20
1,664
Kirill Mazur retweeted
Andrew Davison
@AjdDavisonJun 22
Just announced: #CVPR2026 Best Demo Award for KV-Tracker. Congrats to Marwan and co-authors. And thanks to @deepfry_n, @shinjeong99 for massive help running the demo. That's 4 CVPR Best Demo Awards/Honourable Mentions in 3 years for our lab at Imperial! Proud of our demo culture.
Marwan Taher@marwan_ptr19 Dec 2025
How can we run reconstruction models like π³ and Depth Anything 3 in real-time? We present KV-Tracker, a training-free approach, for real-time tracking of scenes and objects. Achieving up to 30 FPS! With @alzugarayign, @makezur, @XinKong_IC and @AjdDavison
2
20
1
217
23,767
Kirill Mazur retweeted
Marwan Taher@marwan_ptrJun 6
Wanna see a real-time demo of KV-Tracker? Stop by in ExHall F today 11:45 - 13:45! #CVPR2026
2
12
1
54
4,964
How to build complete 4D reconstructions from videos? Swing by 4DPM oral presentation today: Mile High Ballroom 3A - 4A, 13:00 #CVPR2026
4
8
2
108
11,032
code is released too: github.com/makezur/4D_PM project page: makezur.github.io/4DPM/

GitHub - makezur/4D_PM: [CVPR 2026 Oral] 4D Primitive-Mâché: Glueing Primitives for Persistent 4D...

[CVPR 2026 Oral] 4D Primitive-Mâché: Glueing Primitives for Persistent 4D Scene Reconstruction - makezur/4D_PM

github.com
3
688
4DPM got selected for an oral presentation at #CVPR2026 🤠
Kirill Mazur@makezur18 Dec 2025
Introducing 4D Primitive-Mâché (4DPM), a new method for replayable 4D reconstruction from monocular videos. We split dynamic scenes into 3D primitives and recover their motion. 4DPM can infer object positions even after they leave view. Joint work with @marwan_ptr @AjdDavison
3
5
65
7,210
accepted to #CVPR2026 😎
Kirill Mazur@makezur18 Dec 2025
Introducing 4D Primitive-Mâché (4DPM), a new method for replayable 4D reconstruction from monocular videos. We split dynamic scenes into 3D primitives and recover their motion. 4DPM can infer object positions even after they leave view. Joint work with @marwan_ptr @AjdDavison
1
6
86
7,169
project page: makezur.github.io/4DPM/

4DPM — 4D Primitive-Mâché

Glueing Primitives for Persistent 4D Scene Reconstruction — paper, video and results.

makezur.github.io
215
4D Primitive-Mâché: Glueing Primitives for Persistent 4D Scene Reconstruction @makezur, @marwan_ptr, @AjdDavison tl;dr: improve SuperPrimitive; scenes->3D primitives->sparse per-primitive SE(3) poses (+2D correspondences)->per-pixel motion fields arxiv.org/abs/2512.16564
7
33
1,935
Kirill Mazur retweeted
Marwan Taher@marwan_ptr19 Dec 2025
How can we run reconstruction models like π³ and Depth Anything 3 in real-time? We present KV-Tracker, a training-free approach, for real-time tracking of scenes and objects. Achieving up to 30 FPS! With @alzugarayign, @makezur, @XinKong_IC and @AjdDavison
11
99
6
742
87,717
Introducing 4D Primitive-Mâché (4DPM), a new method for replayable 4D reconstruction from monocular videos. We split dynamic scenes into 3D primitives and recover their motion. 4DPM can infer object positions even after they leave view. Joint work with @marwan_ptr @AjdDavison
5
25
4
179
33,384
more replies
4DPM handles multiple moving entities with distinct trajectories. The result is a complete, replayable 4D reconstruction of all observed scene elements at every timestamp.
1
1
5
877
Our method cuts 3D primitives out of the outputs of a feed-forward reconstruction model (π³) and then glues them across time. Each primitive’s motion is represented compactly as a single SE(3) pose, inferred from estimated 2D correspondences via an optimisation pipeline.
6
625
Load more