Martin Oswald
@martin-r-oswald.bsky.social
Doing research in 3D computer vision!
Assist. Prof. @UvA Amsterdam | Prev. ETH Zurich | TUM
Assist. Prof. @UvA Amsterdam | Prev. ETH Zurich | TUM
Reposted by Martin Oswald
IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes
Carl Lindström, Mahan Rafidashti, Maryam Fatemi, Lars Hammarstrand, @martin-r-oswald.bsky.social, Lennart Svensson
tl;dr: coherent instances->dynamic objects
arxiv.org/abs/2511.19235
Carl Lindström, Mahan Rafidashti, Maryam Fatemi, Lars Hammarstrand, @martin-r-oswald.bsky.social, Lennart Svensson
tl;dr: coherent instances->dynamic objects
arxiv.org/abs/2511.19235
November 25, 2025 at 3:07 PM
IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes
Carl Lindström, Mahan Rafidashti, Maryam Fatemi, Lars Hammarstrand, @martin-r-oswald.bsky.social, Lennart Svensson
tl;dr: coherent instances->dynamic objects
arxiv.org/abs/2511.19235
Carl Lindström, Mahan Rafidashti, Maryam Fatemi, Lars Hammarstrand, @martin-r-oswald.bsky.social, Lennart Svensson
tl;dr: coherent instances->dynamic objects
arxiv.org/abs/2511.19235
Reposted by Martin Oswald
🎉#3DV2026 decisions are out!
Can’t wait to see everyone in Vancouver 🇨🇦🏔️🌊
Can’t wait to see everyone in Vancouver 🇨🇦🏔️🌊
November 5, 2025 at 11:55 PM
🎉#3DV2026 decisions are out!
Can’t wait to see everyone in Vancouver 🇨🇦🏔️🌊
Can’t wait to see everyone in Vancouver 🇨🇦🏔️🌊
Surprisingly, “Open-vocabulary” segmentation usually isn’t that open — most methods still depend on costly human labeling, whether through user prompts or human-annotated training data.
October 23, 2025 at 9:29 PM
Surprisingly, “Open-vocabulary” segmentation usually isn’t that open — most methods still depend on costly human labeling, whether through user prompts or human-annotated training data.
Join us this afternoon!
Who needs all data at once?
Learn more about continual/online approaches for 3D scene understanding:
#ICCV2025 Workshop on Neural SLAM
📅 Sunday, October 19, 2025, 1-5PM HST
📍 Room 304 A
📢 Speakers: Federico Tombari, Jakob Engel, @lucacarlone.bsky.social, @akanazawa.bsky.social
Learn more about continual/online approaches for 3D scene understanding:
#ICCV2025 Workshop on Neural SLAM
📅 Sunday, October 19, 2025, 1-5PM HST
📍 Room 304 A
📢 Speakers: Federico Tombari, Jakob Engel, @lucacarlone.bsky.social, @akanazawa.bsky.social
October 19, 2025 at 9:11 PM
Join us this afternoon!
Who needs all data at once?
Learn more about continual/online approaches for 3D scene understanding:
#ICCV2025 Workshop on Neural SLAM
📅 Sunday, October 19, 2025, 1-5PM HST
📍 Room 304 A
📢 Speakers: Federico Tombari, Jakob Engel, @lucacarlone.bsky.social, @akanazawa.bsky.social
Learn more about continual/online approaches for 3D scene understanding:
#ICCV2025 Workshop on Neural SLAM
📅 Sunday, October 19, 2025, 1-5PM HST
📍 Room 304 A
📢 Speakers: Federico Tombari, Jakob Engel, @lucacarlone.bsky.social, @akanazawa.bsky.social
October 17, 2025 at 1:59 PM
Who needs all data at once?
Learn more about continual/online approaches for 3D scene understanding:
#ICCV2025 Workshop on Neural SLAM
📅 Sunday, October 19, 2025, 1-5PM HST
📍 Room 304 A
📢 Speakers: Federico Tombari, Jakob Engel, @lucacarlone.bsky.social, @akanazawa.bsky.social
Learn more about continual/online approaches for 3D scene understanding:
#ICCV2025 Workshop on Neural SLAM
📅 Sunday, October 19, 2025, 1-5PM HST
📍 Room 304 A
📢 Speakers: Federico Tombari, Jakob Engel, @lucacarlone.bsky.social, @akanazawa.bsky.social
Reposted by Martin Oswald
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
@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
October 7, 2025 at 11:17 AM
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
@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
Reposted by Martin Oswald
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
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
September 23, 2025 at 7:12 PM
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
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
Reposted by Martin Oswald
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
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
September 18, 2025 at 10:48 AM
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
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
Reposted by Martin Oswald
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...
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...
September 5, 2025 at 2:48 PM
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...
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...
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...
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...
September 5, 2025 at 2:48 PM
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...
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...
We have extended the submission deadline for the proceedings track to July 5!
#ICCV2025 NeuSLAM Workshop
sites.google.com/view/neuslam...
#ICCV2025 NeuSLAM Workshop
sites.google.com/view/neuslam...
July 3, 2025 at 3:17 PM
We have extended the submission deadline for the proceedings track to July 5!
#ICCV2025 NeuSLAM Workshop
sites.google.com/view/neuslam...
#ICCV2025 NeuSLAM Workshop
sites.google.com/view/neuslam...
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...
Your #ICCV2025 paper got accepted? Congrats! Give it even more visibility by joining our nectar track.
More info: sites.google.com/view/neuslam...
June 27, 2025 at 4:48 PM
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...
Your #ICCV2025 paper got accepted? Congrats! Give it even more visibility by joining our nectar track.
More info: sites.google.com/view/neuslam...
Reposted by Martin Oswald
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
@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
June 10, 2025 at 7:13 PM
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
@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
Reposted by Martin Oswald
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
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
June 11, 2025 at 3:06 PM
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
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
Reposted by Martin Oswald
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/
vladimiryugay.github.io/game/
June 10, 2025 at 12:06 PM
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/
vladimiryugay.github.io/game/
Reposted by Martin Oswald
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
Andrea Conti, @mattpoggi.bsky.social, Valerio Cambareri,
@martin-r-oswald.bsky.social, Stefano Mattoccia
arxiv.org/abs/2504.16545
April 24, 2025 at 1:02 PM
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
Andrea Conti, @mattpoggi.bsky.social, Valerio Cambareri,
@martin-r-oswald.bsky.social, Stefano Mattoccia
arxiv.org/abs/2504.16545
Reposted by Martin Oswald
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
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
April 18, 2025 at 1:09 PM
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
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
Reposted by Martin Oswald
Reposted by Martin Oswald
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
By Fei-Fei Li @drfeifei.bsky.social
from Stanford & World Labs
Checkout worldlabs.ai
March 27, 2025 at 7:03 AM
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
By Fei-Fei Li @drfeifei.bsky.social
from Stanford & World Labs
Checkout worldlabs.ai
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
Lunch break with podium discussion at #3DV2025.
@3dvconf.bsky.social
March 27, 2025 at 5:03 AM
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
Lunch break with podium discussion at #3DV2025.
@3dvconf.bsky.social
Reposted by Martin Oswald
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!
They both showed that 10+years of focused research on your passion problem are needed to make a real difference.
Research needs creativity!
March 27, 2025 at 4:01 AM
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!
They both showed that 10+years of focused research on your passion problem are needed to make a real difference.
Research needs creativity!
Reposted by Martin Oswald
Reposted by Martin Oswald
Keynote2: Reconstructing Everything
By Noah Snavely (@snavely.bsky.social )
from Cornell Tech & Google Deepmind
Noah Snavely: cs.cornell.edu/~snavely/
By Noah Snavely (@snavely.bsky.social )
from Cornell Tech & Google Deepmind
Noah Snavely: cs.cornell.edu/~snavely/
March 27, 2025 at 3:47 AM
Keynote2: Reconstructing Everything
By Noah Snavely (@snavely.bsky.social )
from Cornell Tech & Google Deepmind
Noah Snavely: cs.cornell.edu/~snavely/
By Noah Snavely (@snavely.bsky.social )
from Cornell Tech & Google Deepmind
Noah Snavely: cs.cornell.edu/~snavely/
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
The first 4 speakers and session chair Or Litany during the Q&A session.
@3dvconf.bsky.social
March 27, 2025 at 3:09 AM
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
The first 4 speakers and session chair Or Litany during the Q&A session.
@3dvconf.bsky.social
Exiting keynote talk on "Reconstructing Everything" by Noah Snavely (@snavely.bsky.social) at #3DV2025 today.
@3dvconf.bsky.social
@3dvconf.bsky.social
March 27, 2025 at 1:53 AM
Exiting keynote talk on "Reconstructing Everything" by Noah Snavely (@snavely.bsky.social) at #3DV2025 today.
@3dvconf.bsky.social
@3dvconf.bsky.social