Eric Dexheimer
@eric_dexheimer
Followers
667
Following
1K
Media
14
Statuses
46
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 @joeaortiz: Genie3 is a real-time, interactive and general world model! Excited to see it used for training agents. It's also really fun….
0
2
0
RT @brenthyi: July has been a big month for Viser!.- Released v1.0.0😊.- We did some writing. Some demos👇
0
79
0
RT @SucarEdgar: Good essay on the analogy of the stone soup tale to AI misconception. More emphasis is placed on individual AI models and t….
simons.berkeley.edu
For some time, I’ve argued that a common conception of AI is misguided. This is the idea that AI systems like large language and vision models are individual intelligent agents, analogous to human...
0
1
0
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
8
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
56
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
260
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