15 Photos and videos
Pinned Tweet
2 Mar 2024
Excited to introduce ๐๐ฆ๐๐ก๐! (#CVPR2024)
baegwangbin.github.io/DSINE/
We push the limits of single-image surface normal estimation by rethinking the inductive biases needed for the task.
See you in Seattle!
7
114
642
56,373
Try Tesla Robotaxi in Dallas & Houston!
5,443
10,332
82,160
24,993,139
Gwangbin Bae retweeted
Mar 5
Excited to introduce RoEL, accepted to T-RO!
โ What 3D representation to use for event-based reconstruction?
๐ก Event cameras capture edges; we reconstruct them as ๐๐ ๐ฅ๐ข๐ง๐๐ฌ.
We present a robust pipeline: from reliable correspondence search to Grassmannian optimization.
1
1
3
162
Just started Tesla Robotaxi drives in Austin with no safety monitor in the car.
Congrats to the @Tesla_AI team!
If youโre interested in solving real-world AI, which is likely to lead to AGI imo, join Tesla AI. Solving real-world AI for Optimus will be 100X harder than cars.
3,876
8,922
69,718
8,959,151
Gwangbin Bae retweeted
28 May 2025
Visual SLAM has made major success in static scenes โ now letโs explore the dynamic world we live in!
At #CVPR2025, we introduce 4DTAM, 4D Tracking & Mapping using dynamic surface Gaussians optimized through diff. rendering.
muskie82.github.io/4dtam/
w/ @BaeGwangbin @AjdDavison
8
55
317
32,070
Gwangbin Bae retweeted
16 Dec 2024
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)
42
253
1,433
203,565
Gwangbin Bae retweeted
25 Sep 2024
COMO will be presented as an ๐จ๐ซ๐๐ฅ at #ECCV2024!
Also come see the ๐ฅ๐ข๐ฏ๐ ๐๐๐ฆ๐จ 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/como/
3 Apr 2024
How can we infer 3D-consistent poses and dense geometry in real-time given only RGB images?
๐๐ข๐ ๐ข 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
18
106
11,213
19 Jul 2024
First time giving a talk at BMVA Computer Vision Summer School. It was great meeting students and exchanging ideas!
19 Jul 2024
Dr Gwangbin Bae @BaeGwangbin delivered on a talk on "Always-on Perception for 3D Computer Vision" in the 27th BMVA Computer Vision Summer School in Durham University.
1
5
42
2,780
Gwangbin Bae retweeted
2 Jul 2024
Our lab's #SpatialAI demo guidelines:
1. Build demos (real-time good visualisations) *while* doing the actual research.
2. You learn more from 3 minutes with a live demo than any dataset results.
3. Show your demo to as many people as possible. Don't worry if it's not perfect.
2 Jul 2024
We won Best Demo at #CVPR2024 for Gaussian Splatting SLAM (@HideMatsu82 @rmurai0610). Also: Best Demo Honourable Mention for SuperPrimitives (@makezur @BaeGwangbin)! Proud of our whole group at @ICComputing. Demos make big impact, and are also fun! cvpr.thecvf.com/Conferences/โฆ
3
10
103
16,830
23 Jun 2024
On my way to London after an unforgettable week at #CVPR2024. It was my first in-person CVPR and I loved every moment of it. A big thank you to everyone who came to my talk/poster!
1
2
51
5,325
Gwangbin Bae retweeted
21 Jun 2024
Reminder of the live demos of DSINE (real-time high quality normals) and SuperPrimitives (normals integrated into real-time monocular dense SLAM) in the demo session all day today at #CVPR2024.
14 Jun 2024
SuperPrimitives will be presented at #CVPR next week (Wednesday), along with a ๐ฟ๐ฒ๐ฎ๐น-๐๐ถ๐บ๐ฒ ๐ฑ๐ฒ๐บ๐ผ on Friday!
Our new representation enables dense monocular 3D reconstruction in real-time. No poses required!
Project page: makezur.github.io/SuperPrimiโฆ
1
2
30
4,062
20 Jun 2024
Here is the presentation schedule for ๐๐ฆ๐๐ก๐ (#CVPR2024)
See you tomorrow!
2
6
57
9,335
17 Jun 2024
๐๐ฆ๐๐ก๐ will be presented as an Oral at #CVPR2024!
Come to our talk - ๐ข๐ฟ๐ฎ๐น๐ ๐ฏ๐, ๐ต๐๐ ๐ผ๐ป ๐ง๐ต๐๐ฟ๐๐ฑ๐ฎ๐ - to hear about the motivation/insights behind this project and how surface normal cues can be incorporated in your research.
22
161
9,305
Gwangbin Bae retweeted
14 Jun 2024
SuperPrimitives will be presented at #CVPR next week (Wednesday), along with a ๐ฟ๐ฒ๐ฎ๐น-๐๐ถ๐บ๐ฒ ๐ฑ๐ฒ๐บ๐ผ on Friday!
Our new representation enables dense monocular 3D reconstruction in real-time. No poses required!
Project page: makezur.github.io/SuperPrimiโฆ
3
42
208
30,797
24 Apr 2024
๐ข Code release for ๐๐ฆ๐๐ก๐ (#CVPR2024 - Oral)
DSINE gives you surface normal prediction ( uncertainty) in real-time. We have released the code for training, testing, and running real-time demos. Try it yourself!
github.com/baegwangbin/DSINE
8
118
656
83,296
Gwangbin Bae retweeted
3 Apr 2024
How can we infer 3D-consistent poses and dense geometry in real-time given only RGB images?
๐๐ข๐ ๐ข 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
3
54
265
41,784
5 Apr 2024
Finally released the code for ๐จ-๐๐ฅ๐-๐ ๐!
๐จ-๐๐ฅ๐-๐ ๐ estimates camera rotation in real-time by aligning the predicted surface normals to global principal directions.
Try our real-time demo with a webcam, or simply provide a link to a YouTube video.
5 Apr 2024
๐๐ผ๐ฑ๐ฒ ๐ฟ๐ฒ๐น๐ฒ๐ฎ๐๐ฒ for U-ARE-ME !
Try it out yourself on any video:
github.com/callum-rhodes/U-Aโฆ
๐๐๐ ๐๐ฉ ๐ก๐๐ซ๐ ๐๐ฃ ๐๐๐ฉ๐๐ค๐ฃ!
@DoC_Rhodes_ @BaeGwangbin @AjdDavison
1
15
70
6,774