Marwan Taher

PhD student at the Dyson Robotics Lab @ Imperial College London.

[Marwan Taher @marwan_ptr]

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

[Marwan Taher @marwan_ptr]

Project page: https://t.co/NmY4AwLz7M

Code: https://t.co/QZPEiPCSbD

[Marwan Taher @marwan_ptr]

Wanna see a real-time demo of KV-Tracker?
Stop by in ExHall F today 11:45 - 13:45!

#CVPR2026

[Kirill Mazur @makezur]

How to build complete 4D reconstructions from videos? Swing by 4DPM oral presentation today: Mile High Ballroom 3A - 4A, 13:00

#CVPR2026

[Kirill Mazur @makezur]

4DPM got selected for an oral presentation at #CVPR2026 🤠

[Marwan Taher @marwan_ptr]

KV-Tracker has been accepted to #CVPR2026!

[Marwan Taher @marwan_ptr]

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

[Marwan Taher @marwan_ptr]

More results and the paper can be found here: https://t.co/wPfzJXdt2w

Video: https://t.co/uITVUch8D0

[Marwan Taher @marwan_ptr]

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

[Marwan Taher @marwan_ptr]

KV-Tracker enables object-level reconstruction and tracking when provided with an object mask.

The KV-cache can be saved and used later without any special initialisation procedure.

[Marwan Taher @marwan_ptr]

Per-frame geometry from π³ is split into primitives via segmentation and tracked over time using dense 2D point tracks. With a compact per primitive pose, geometry is densely aligned, stitching primitives to create a complete reconstruction of the observed scene components.

[Kirill Mazur @makezur]

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

[Marwan Taher @marwan_ptr]

ACE-SLAM naturally handles loop closure without special treatment, robustly deals with dynamic objects, while remaining lightweight (small MLP) and computationally efficient—making this representation compelling for SLAM.

[Ignacio Alzugaray @alzugarayign]

Excited to present ACE-SLAM, the first neural SLAM to use Scene Coordinate Regression as an implicit map representation

Efficient (real-time from live stream), compressive (neural maps <1MB) and robust to dynamic scenes

With @marwan_ptr and @AjdDavison
https://t.co/tMsD5hTkB3

[Xin Kong @XinKong_IC]

🚀 Excited to share CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis!

Let’s recon 3D world generatively. CausNVS handles any number of input views, synthesizes novel views autoregressively, enables interactive streaming and flexible N-to-M NVS.

[Riku Murai @rmurai0610]

Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation.

Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.

With @eric_dexheimer*, @AjdDavison (*Equal Contribution)

[Marwan Taher @marwan_ptr]

@_ayoungk @rmurai0610

[Marwan Taher @marwan_ptr]

@_Sir_MuEl @_ayoungk https://t.co/cKcYNS8Chf

[Marwan Taher @marwan_ptr]

EscherNet will be presented tomorrow at #CVPR. But *now* you can drop a couple of images into our Hugging Face demo to try it out!

https://t.co/PaiXGJlgoF

[Xin Kong @XinKong_IC]

Tired of single image to 3D? Check out EscherNet tomorrow @CVPR that can take flexible number of views for 3D generation!

THURSDAY, JUNE 20
ORAL: 9:00-10:30, SUMMIT BALLROOM (TOP FLOOR)
POSTER: 10:30-12:00, ARCH 4A-E, #69

Try our @Gradio online demo
https://t.co/PAaJdgRaZt

[Marwan Taher @marwan_ptr]

Don't miss the real-time demo of SuperPrimitives at #CVPR!!

[Kirill Mazur @makezur]

SuperPrimitives will be presented at #CVPR next week (Wednesday), along with a 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝗱𝗲𝗺𝗼 on Friday!

Our new representation enables dense monocular 3D reconstruction in real-time. No poses required!

Project page: https://t.co/l360soWiAz

[Aalok Patwardhan @AalokPat]

From RGB images we can estimate camera rotation, *without* knowledge of camera intrinsics. This also leads to some cool downstream applications - it can complement an IMU .. we call it U-ARE-ME!
@AjdDavison @DoC_Rhodes94 @BaeGwangbin