Eric Dexheimer
@eric_dexheimer
Followers
668
Following
1K
Media
14
Statuses
43
PhD student at Dyson Robotics Lab, Imperial College London
London, UK
Joined March 2022
We’ve had fun testing the limits of MASt3R-SLAM on in-the-wild videos. Here’s the drone video of a Minnesota bowling alley that we’ve always wanted to reconstruct! Different scene scales, dynamic objects, specular surfaces, and fast motion.
MASt3R-SLAM code release!. Try it out on videos or with a live camera. Work with @eric_dexheimer*, @AjdDavison (*Equal Contribution).
7
22
186
RT @AjdDavison: Well done to Riku and @eric_dexheimer on Best Demo Honourable Mention for MASt3R-SLAM at #CVPR2025. That's 3 best demo awar….
0
7
0
RT @rmurai0610: We (with @eric_dexheimer) will be demoing MASt3R-SLAM @CVPR today 16:00-18:00, ExHall B, 9. Come and see the limits of our….
0
15
0
The paper is called “The Structure of Locally Orderless Images” by Jan J. Koenderink and Andrea J. Van Doorn. There’s also some nice discussion on scenes and observations.
link.springer.com
International Journal of Computer Vision - We propose a representation of images in which a global, but not a local topology is defined. The topology is restricted to resolutions up to the extent...
0
0
3
This is a very cool paper. It reminds me of a work by Jan Koenderink where we can visual image scale space not only by the conventional blurring perspective, but also by disordering the image pixels. Disordering retains information in a manner similar to impressionist paintings.
Our #Siggraph25 work found a simple, nearly one-line change that greatly eases neural field optimization for a wide variety of existing representations. “Stochastic Preconditioning for Neural Field Optimization” w/ @merlin_ND @_AlecJacobson @nmwsharp
5
7
95
RT @Suddhus: I'm a featured interview in our latest behind-the-scenes release! We break down the ML and perception that drives the whole-bo….
0
7
0
RT @HideMatsu82: Visual SLAM has made major success in static scenes — now let’s explore the dynamic world we live in!. At #CVPR2025, we in….
0
55
0
Here is a fun example with a continuous transition between distinct 3D scenes!
1
1
21
RT @gabriberton: Excited to release the first worldwide aerial image localization method (and demo!).Take an aerial or satellite image from….
0
27
0
RT @rmurai0610: Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MA….
0
261
0
RT @Suddhus: For robot dexterity, a missing piece is general, robust perception. Our new @SciRobotics work combines multimodal sensing with….
0
14
0
RT @rmurai0610: We'll be presenting "Distributed Simultaneous Localisation and Auto-Calibration using GBP" at #IROS2024. We show that distr….
0
18
0
COMO will be presented as an 𝐨𝐫𝐚𝐥 at #ECCV2024!. Also come see the 𝐥𝐢𝐯𝐞 𝐝𝐞𝐦𝐨 of our compact 3D representation for real-time monocular SLAM. Oral: Session 2C at 1:40 PM on Tue 1 Oct.Poster: #181 at 4:30-6:30 PM on Tue 1 Oct.Demo: Thurs 3 Oct AM.
edexheim.github.io
We present COMO, a real-time monocular mapping and odometry system that encodes dense geometry via a compact set of 3D anchor points. Decoding anchor point projections into dense geometry via...
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: Work with @AjdDavison. 1/n
0
18
107
RT @sethnabarro: Excited to be at ICML! I'll be presenting a poster on GBP Learning — our approach to train deep networks using Gaussian be….
0
5
0
RT @BaeGwangbin: 📢 Code release for 𝗗𝗦𝗜𝗡𝗘 (#CVPR2024 - Oral). DSINE gives you surface normal prediction (+ uncertainty) in real-time. We ha….
0
120
0
RT @anagh_malik: 📢📢📢 A pulse of light takes ~3ns to pass through a Coke bottle—100 million times less than it takes you to blink. Our work….
0
40
0
Check out our code to run the real-time demo with your own camera!. 𝗖𝗢𝗠𝗢: 𝗖𝗼𝗺𝗽𝗮𝗰𝘁 𝗠𝗮𝗽𝗽𝗶𝗻𝗴 𝗮𝗻𝗱 𝗢𝗱𝗼𝗺𝗲𝘁𝗿𝘆.Code: Video: Dyson Robotics Lab, Imperial College London.4/4.
0
6
36