From Rays to Projections: Better Inputs for Feed-Forward View Synthesis
Zirui Wu, Zeren Jiang, @martin-r-oswald.bsky.social, Jie Song
tl;dr: context views->MapAnything->depth maps->rasterizing->point cloud projection image->fine-tuning
arxiv.org/abs/2601.05116
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
🎉#3DV2026 decisions are out!
Can’t wait to see everyone in Vancouver 🇨🇦🏔️🌊
Also, our follow-up work and extension to 3D point-clouds has been presented at CVPR2025:
openaccess.thecvf.com/content/CVPR...
This work has seen many R2's and the in meantime other methods have appeared with the name "vocabulary-free". While the input is indeed vocabulary-free, the method is not, it has to be auto-generated in order to enumerate all objects in a scene.
Learn more today @ #ICCV2025:
📅 #418 Poster Session 5 10:45-12:45 HST
📍 Exhibit Hall I
🌐 ozzyou.github.io/autoseg.gith...
We present "Auto-vocabulary segmentation" in which the vocabulary is auto-generated with a captioning method which is then used by the segmentation method.
We also introduce an automatic vocabulary mapping for evaluation on human-labeled datasets which typically have a much smaller vocabulary.
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.
A few more impression from the Neural SLAM workshop today.
Thanks so much to our keynote speakers for making this such an insightful and memorable event:
- Luca Carlone @lucacarlone.bsky.social
- Angjoo Kanazawa @akanazawa.bsky.social
- Federico Tombari @
- Jakob Engel @jajuengel
👏👏🙏
Our fourth keynote today by Jakob Engel.
📍 Room 304 A
🌐 sites.google.com/view/neuslam...
#ICCV2025
Federico Tombari during his keynote right now.
📍 Room 304 A
🌐 sites.google.com/view/neuslam...
#iccv25
Angjoo Kanazawa giving her keynote talk now.
📍 Room 304 A
🌐 sites.google.com/view/neuslam...
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
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
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
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
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...
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...
We have extended the submission deadline for the proceedings track to July 5!
#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...
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
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
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/
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
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
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
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
Third and last Q&A session of the Nectar Track at #3DV2025.
Thanks to all the speakers!
@3dvconf.bsky.social
