Lightnews — Scholar-powered news

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · 2d

Visual Odometry with Transformers

@vyuga3d.bsky.social, Duy-Kien Nguyen, Theo Gevers, @cgmsnoek.bsky.social, @martin-r-oswald.bsky.social

tl;dr: DUSt3R encoder->image token embeddings (+camera embeddings)->time/space attention decoder->rotation+translation

arxiv.org/abs/2510.03348

1 8

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · 15d

ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos

Shi Chen, Erik Sandström, Sandro Lombardi, Siyuan Li, @martin-r-oswald.bsky.social

tl;dr: Splat-SLAM+SAM2->tracking; Motion Scaffolds+GS->dynamic

arxiv.org/abs/2509.17864

3 3

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · 21d

MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping

Zhihao Cao, Hanyu Wu, Li Wa Tang, Zizhou Luo, Zihan Zhu, Wei Zhang, @marcpollefeys.bsky.social, @martin-r-oswald.bsky.social

tl;dr: in title

arxiv.org/abs/2509.14191

1 4

Reposted by Martin Oswald

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

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

Martin Oswald @martin-r-oswald.bsky.social · Jul 3

We have extended the submission deadline for the proceedings track to July 5!

#ICCV2025 NeuSLAM Workshop

sites.google.com/view/neuslam...

2

Martin Oswald @martin-r-oswald.bsky.social · Jun 27

Your #ICCV2025 paper got rejected? Give it another try and submit to our proceedings track!

Your #ICCV2025 paper got accepted? Congrats! Give it even more visibility by joining our nectar track.

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

5 11

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · Jun 10

Gaussian Mapping for Evolving Scenes

@vyuga3d.bsky.social, Thies Kersten, @lucacarlone.bsky.social, Theo Gevers, @martin-r-oswald.bsky.social, Lukas Schmid

tl;dr: semantic consistency->3DGS->environment changes; covisibility-bsed keyframe management->mask stale areas

arxiv.org/abs/2506.06909

2 6

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · Jun 11

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting

Mengjiao Ma, Qi Ma, Yue Li, Jiahuan Cheng, Runyi Yang, Bin Ren, Nikola Popovic, Mingqiang Wei, Nicu Sebe, Luc Van Gool, Theo Gevers, @martin-r-oswald.bsky.social, Danda Pani Paudel

arxiv.org/abs/2506.08710

1 1

Reposted by Martin Oswald

Vladimir Yugay @vyuga3d.bsky.social · Jun 10

Introducing “Gaussian Mapping of Evolving Scenes”! We present an RGBD mapping system with novel view synthesis capabilities that accurately reconstruct scenes that change over time
vladimiryugay.github.io/game/

1 2 3

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · Apr 24

ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration

Andrea Conti, @mattpoggi.bsky.social, Valerio Cambareri,
@martin-r-oswald.bsky.social, Stefano Mattoccia

arxiv.org/abs/2504.16545

1 1 1

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · Apr 18

ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos

Zetong Zhang, Manuel kaufmann, @lixinxue.bsky.social, Jie Song, @martin-r-oswald.bsky.social

tl;dr: human shape & pose priors from SMPL+monocular geometric prior from DAv2+GS SLAM

arxiv.org/abs/2504.13167

1 3

Reposted by Martin Oswald

International Conference on 3D Vision @3dvconf.bsky.social · Mar 27

1 1

Reposted by Martin Oswald

International Conference on 3D Vision @3dvconf.bsky.social · Mar 27

Keynote3 -- From Seeing to Doing: Ascending the Ladder of Visual Intelligence

By Fei-Fei Li @drfeifei.bsky.social
from Stanford & World Labs

Checkout worldlabs.ai

1 1 7

Martin Oswald @martin-r-oswald.bsky.social · Mar 27

What a great line-up of experts to listen to like a "lunch podcast" on 3D Vision topics.
Lunch break with podium discussion at #3DV2025.
@3dvconf.bsky.social

1 1 10

Martin Oswald @martin-r-oswald.bsky.social · Mar 27

Third and last Q&A session of the Nectar Track at #3DV2025.
Thanks to all the speakers!
@3dvconf.bsky.social

1 1 4

Reposted by Martin Oswald

Dima Damen @dimadamen.bsky.social · Mar 27

Both keynotes @3dvconf.bsky.social from Google Deepmind star researchers @jonbarron.bsky.social and @snavely.bsky.social were a joy to attend.
They both showed that 10+years of focused research on your passion problem are needed to make a real difference.
Research needs creativity!

2 19

Martin Oswald @martin-r-oswald.bsky.social · Mar 27

Second Q&A session of the Nectar Track at #3DV2025.
@3dvconf.bsky.social

1 1 1

Reposted by Martin Oswald

International Conference on 3D Vision @3dvconf.bsky.social · Mar 27

1 1

Reposted by Martin Oswald

International Conference on 3D Vision @3dvconf.bsky.social · Mar 27

Keynote2: Reconstructing Everything

By Noah Snavely (@snavely.bsky.social )
from Cornell Tech & Google Deepmind

Noah Snavely: cs.cornell.edu/~snavely/

1 2 9

Martin Oswald @martin-r-oswald.bsky.social · Mar 27

Impressions of the Nectar Track Session at #3DV2025 which provides great 3D Vision works additional visibility.
The first 4 speakers and session chair Or Litany during the Q&A session.
@3dvconf.bsky.social

1 1 3

Martin Oswald @martin-r-oswald.bsky.social · Mar 27

Exiting keynote talk on "Reconstructing Everything" by Noah Snavely (@snavely.bsky.social) at #3DV2025 today.
@3dvconf.bsky.social

1 5

Reposted by Martin Oswald

International Conference on 3D Vision @3dvconf.bsky.social · Mar 26

The Best paper Honorable Mention Award goes to MeshUp!

#3DV2025

2 17

Reposted by Martin Oswald

International Conference on 3D Vision @3dvconf.bsky.social · Mar 26

Best Paper Award #3DV2025 goes to "An object is Worth 64x64 Pixels"!

1 15

Reposted by Martin Oswald

Zhenjun Zhao @ericzzj.bsky.social · Mar 25

Splat-LOAM: Gaussian Splatting LiDAR Odometry and Mapping

Emanuele Giacomini, Luca Di Giammarino, Lorenzo De Rebotti, Giorgio Grisetti, @martin-r-oswald.bsky.social

tl;dr: LiDAR measurements->spherical projection->image-like representation->2DGS

arxiv.org/abs/2503.17491

2 4