Lightnews — Scholar-powered news

Reposted by Vincent Leroy

Vladimir Yugay @vyuga3d.bsky.social · 2d

📽️ Check out Visual Odometry Transformer! VoT is an end-to-end model for getting accurate metric camera poses from monocular videos.

vladimiryugay.github.io/vot/

1 4 10

Reposted by Vincent Leroy

Bart Duisterhof @bardienus.bsky.social · 19d

RaySt3R was accepted to NeurIPS! Check out the HuggingFace demo for image to 3D in cluttered scenes huggingface.co/spaces/bartd...

2 5

Vincent Leroy @vincentleroy.bsky.social · 20d

This or some kind of PRoPe arxiv.org/abs/2507.10496

Cameras as Relative Positional Encoding

Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-vi...

arxiv.org

1 3

Vincent Leroy @vincentleroy.bsky.social · 20d

Yes exactly if you are dealing with unordered image collections. The same certainly cannot be said when dealing with videos where the displacement between two frames makes more sense.

1 3

Reposted by Vincent Leroy

Johan Edstedt @parskatt.bsky.social · 21d

Wrt to RoPE: People are applying it wrongly for multi-view, if you do it VGGT style you will mix the positions of all the images. You should do it independently (i.e. no rope between images).

2 1 5

Reposted by Vincent Leroy

Dmytro Mishkin @ducha-aiki.bsky.social · 21d

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Nikhil Keetha et 16 al.

tl;dr: VGGT meets Pow3R. No RoPE. Metric scale.
arxiv.org/abs/2509.13414

1/

3 2 17

Reposted by Vincent Leroy

Zhenjun Zhao @ericzzj.bsky.social · 20d

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

@nikv9.bsky.social et al.

tl;dr: flexible input & metric output version of VGGT

arxiv.org/abs/2509.13414

2 2

Reposted by Vincent Leroy

Johan Edstedt @parskatt.bsky.social · 22d

And here is a link to the thesis itself: liu.diva-portal.org/smash/record...

Towards the Next Generation of 3D Reconstruction

liu.diva-portal.org

6 19

Reposted by Vincent Leroy

Dmytro Mishkin @ducha-aiki.bsky.social · 21d

Towards the Next Generation of 3D Reconstruction

@parskatt.bsky.social PhD Thesis.

tl;dr: would be useful in teaching image matching - nice explanations. (too) Fancy and stylish notation. Cool Ack section and cover image.

liu.diva-portal.org/smash/record...

2 8 33

Reposted by Vincent Leroy

Christian Wolf @chriswolfvision.bsky.social · 25d

How to name your method: a comprehensive flow chart

1 10 43

Reposted by Vincent Leroy

Martin Oswald @martin-r-oswald.bsky.social · Sep 5

Want more visibility for your SLAM-related paper at #ICCV2025?

Submit to the Nectar Track of our Neural SLAM workshop before Sep. 15!

We welcome any recently published high-quality papers (ICCV, CVPR, NeurIPS, Arxiv, etc.)!

🌐 More info: sites.google.com/view/neuslam...

3 7

Reposted by Vincent Leroy

NAVER LABS Europe @naverlabseurope.bsky.social · Sep 4

Adding the fab view of Grenoble by night!

1 4

Reposted by Vincent Leroy

Christian Wolf @chriswolfvision.bsky.social · Sep 4

The 4th day of the #PAISS2025 summer school is opened by Jérôme Revaud presenting 'Data-driven 3d vision' and the DUSt3R and MASt3R family of models.

1 2 21

Reposted by Vincent Leroy

Diane Larlus @dlarlus.bsky.social · Sep 4

We couldn't get more lucky with the weather last night for the #PAISS2025 gala - sponsored by @naverlabseurope.bsky.social

2 3 15

Reposted by Vincent Leroy

Diane Larlus @dlarlus.bsky.social · Sep 3

Third day of #PAISS2025 starts strong with a talk from @science4all.org about 'AI Security'

1 3 9

Reposted by Vincent Leroy

franorajic.bsky.social @franorajic.bsky.social · Aug 29

1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.

1 2 8

Reposted by Vincent Leroy

NAVER LABS Europe @naverlabseurope.bsky.social · Aug 25

HOSt3R (Keypoint-free Hand-Object 3D Reconstruction from RGB images) builds upon DUSt3R for unconstrained hand-object 3D reconstruction - example 3D shape output below.
Paper: arxiv.org/abs/2508.16465
More info on @naverlabseurope.bsky.social
@iccv.bsky.social ➡️ tinyurl.com/2p9kcb86
2/2🧵

2 9

Reposted by Vincent Leroy

NAVER LABS Europe @naverlabseurope.bsky.social · Aug 25

Announcing 2 new members of the *St3R family for human-centric 3D vision tasks!
Meet HAMst3R & HOSt3R
@iccv.bsky.social
- HAMSt3R (Human-Aware Multi-view Stereo 3D Reconstruction) extends MASt3R to handle scenes involving people.
Paper: arxiv.org/abs/2508.16433
1/2 🧵

1 4 15

Reposted by Vincent Leroy

Yannis Kalantidis @skamalas.bsky.social · Aug 25

Check out HAMSt3R 🐹 A human-aware multi-view 3D reconstruction method from NLE, accepted at ICCV 2025!

Zhenjun Zhao @ericzzj.bsky.social · Aug 25

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Sara Rojas, Matthieu Armando, Bernard Ghamen, @weinzaepfelp.bsky.social, @vincentleroy.bsky.social, Gregory Rogez

arxiv.org/abs/2508.16433

1 14

Reposted by Vincent Leroy

Dmytro Mishkin @ducha-aiki.bsky.social · Aug 25

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images

Anilkumar Swamy, @vincentleroy.bsky.social @weinzaepfelp.bsky.social Jean-Sébastien Franco, Grégory Rogez

tl;dr: DUSt3R tuned on hands-pose dataset + handcrafted 3D reconstruction system
arxiv.org/abs/2508.16465

5 14

Reposted by Vincent Leroy

Zhenjun Zhao @ericzzj.bsky.social · Aug 25

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction

Sara Rojas, Matthieu Armando, Bernard Ghamen, @weinzaepfelp.bsky.social, @vincentleroy.bsky.social, Gregory Rogez

arxiv.org/abs/2508.16433

1 4 13

Reposted by Vincent Leroy

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 29

All confirmed speakers: Andrew Davison - Nicolas Mansard - Cordelia Schmid - Marc Pollefeys - Michael Gienger - David Novotny - Andrea Vedaldi - Xavier Alameda-Pineda - Eric Brachmann - Fatma Güney - Aniruddha Kembhavi - Daniel Cremers - Adrien Gaidon - Dongwhan Lee

1 1 4

Reposted by Vincent Leroy

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 29

Major announcement ✨registration is OPEN✨
AI for Robotics workshop (4th edition): Spatial AI
🗓️Nov 21-22 Grenoble, France!
Details: tinyurl.com/bdtk2nzs
⭐⭐ 14 confirmed speakers ⭐⭐: 🧵2/3
Poster submissions (travel grant possible): 🧵 3/3
Spread the word!

1 7 19

Reposted by Vincent Leroy

Christian Wolf @chriswolfvision.bsky.social · Jul 29

Naver Labs Europe organizes a Workshop on AI for Robotics in the French Alpes (Grenoble), the 4th edition. This year the topic is 'Spatial AI', registration is open!

NAVER LABS Europe @naverlabseurope.bsky.social · Jul 29

Major announcement ✨registration is OPEN✨
AI for Robotics workshop (4th edition): Spatial AI
🗓️Nov 21-22 Grenoble, France!
Details: tinyurl.com/bdtk2nzs
⭐⭐ 14 confirmed speakers ⭐⭐: 🧵2/3
Poster submissions (travel grant possible): 🧵 3/3
Spread the word!

4 16

Vincent Leroy @vincentleroy.bsky.social · Jul 18

And live performance for conference orals!

1