Kirill Mazur

27 posts

Kirill Mazur

Kirill Mazur

@makezur

PhD student at Dyson Robotics Lab @ Imperial College London

London, UK 参加日 Mayıs 2020
373 フォロー中435 フォロワー
固定されたツイート
Kirill Mazur
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
English
4
25
164
25K
Kirill Mazur がリツイート
Zhenjun Zhao
Zhenjun Zhao@zhenjun_zhao·
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
Zhenjun Zhao tweet mediaZhenjun Zhao tweet mediaZhenjun Zhao tweet mediaZhenjun Zhao tweet media
Français
0
7
33
1.9K
Kirill Mazur がリツイート
Marwan Taher
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
English
10
97
704
64.7K
Kirill Mazur
Kirill Mazur@makezur·
@sha0nk each pixel is only assigned to (at most) one primitive; all segments are also eroded around the edges to compensate for feed-forward reconstruction artifacts around object boundaries
English
0
0
3
248
Kirill Mazur
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
English
4
25
164
25K
Kirill Mazur
Kirill Mazur@makezur·
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.
English
0
0
6
503
Kirill Mazur
Kirill Mazur@makezur·
4DPM handles multiple moving entities with distinct trajectories. The result is a complete, replayable 4D reconstruction of all observed scene elements at every timestamp.
English
1
1
4
706
Kirill Mazur がリツイート
Riku Murai
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)
English
42
255
1.4K
203.2K
Kirill Mazur
Kirill Mazur@makezur·
Curious how DSINE surface normals can be converted into full 3D geometry? Visit our demo of 𝗦𝘂𝗽𝗲𝗿𝗣𝗿𝗶𝗺𝗶𝘁𝗶𝘃𝗲-based real-time 3D reconstruction tomorrow (Friday)! A demo is worth a thousand pictures 🙂 Demo: 10:30 to 18:45, Arch CDE #9 #CVPR #CVPR2024
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: makezur.github.io/SuperPrimitive/

English
0
1
14
1.9K
Kirill Mazur
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: makezur.github.io/SuperPrimitive/
English
3
42
210
30.7K
Kirill Mazur がリツイート
Eric Dexheimer
Eric Dexheimer@eric_dexheimer·
How can we infer 3D-consistent poses and dense geometry in real-time given only RGB images? 𝗖𝗢𝗠𝗢 decodes dense geometry from a compact and optimizable set of 3D anchor points to enforce 3D consistency. Project page: edexheim.github.io/como/ Work with @AjdDavison 1/n
English
4
55
266
41.7K
Kirill Mazur
Kirill Mazur@makezur·
Code release for SuperPrimitives, and it comes with an interactive GUI! #CVPR2024 github.com/makezur/super_… SuperPrimitive is a new 3D representation which enables solving many 3D tasks at the level of image segments.
English
1
37
169
23K

ディスカバー

@marwan_ptr @AjdDavison @alzugarayign @XinKong_IC @sha0nk @eric_dexheimer @vlordier @elonmusk