Kirill Mazur retweeted
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
Kirill Mazur retweeted
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.
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
Kirill Mazur retweeted
Wanna see a real-time demo of KV-Tracker?
Stop by in ExHall F today 11:45 - 13:45!
#CVPR2026
Kirill Mazur retweeted
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
Kirill Mazur retweeted
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
Kirill Mazur retweeted
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)
Kirill Mazur retweeted
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
Kirill Mazur retweeted
Should the complexity of 3D reconstruction tasks be dependent on # of pixels or # of “things” in the image? We use surface normal and segmentation priors to split the image into 2.5D segments and show how this representation can help tackle a wide range of 3D reconstruction tasks
SuperPrimitives enable 3D scene reconstruction at a level of local image regions rather than pixels.
With SuperPrimitves, 3D reconstruction is done simply, thanks to powerful off-the-shelf 2D priors.
project page: makezur.github.io/SuperPrimi…
video: youtu.be/hKYgAf6MoB8
Kirill Mazur retweeted
Excited to share our work on Point-Based Modeling of Human Clothing accepted to ICCV'21! 🥳
🌐 Project page: saic-violet.github.io/point-…
🎬 Video: youtube.com/watch?v=kFrAu415…
📝 Paper: bit.ly/3ax9ei6
Join us on Session 11 at iccv2021.thecvf.com on Oct 13th and 15th















