Noah Snavely
924 posts
Noah Snavely
@Jimantha
3D vision fanatic. Professor @cornell_tech & Researcher @GoogleDeepmind. He or they. https://t.co/m7Rs5xUFfG
New York, NY Katılım Haziran 2008
867 Takip Edilen9.8K Takipçiler
Thank you, Humphrey! It's a real honor to receive this award!
Humphrey Shi@humphrey_shi
Congratulations to Noah Snavely @Jimantha from @Cornell receiving the 2026 Thomas S. Huang Memorial Prize at @CVPR — a well-deserved recognition of his impactful contributions to computer vision research and our community. Remembering Tom & Margaret: youtu.be/QV7WnO9Lk9M?si…
English
@Jimantha Many congratulations Noah! Very well deserved! 🥳
English
Congrats to the team for wining CVPR Best Paper Award!! 🏆 Come to our oral session (Mile High Ballroom 13:00-14:15) and poster (16:00-18:00) today for more details 🚀
Chuhan Zhang@ChuhanZhang5
A SINGLE encoder + decoder for all the 4D tasks! We release 🎯 D4RT (Dynamic 4D Reconstruction and Tracking). 📍 A simple, unified interface for 3D tracking, depth, and pose 🌟 SOTA results on 4D reconstruction & tracking 🚀 Up to 100x faster pose estimation than prior works
English
@Jimantha Congrats Noah! It's always so inspiring to read your papers!
English
We use a sort of @elliottszwu-style strategy to build a dataset of symmetries in architectural scenes, then detect and localize symmetries in new images via signed-distance functions. This is really great work from Hanyu with very nice visuals!
Hanyu Chen@hanyuc1110
Excited to share ArchSym at #CVPR2026! 🏛️ Existing 3D symmetry detectors work well on clean, object-centric data. But what about in the wild? In our work, we tackle 3D-grounded reflectional symmetry detection specifically for real-world architectural landmarks. 🧵[1/7]
English
@kvuongdev Thank you, Khiem! AerialMegaDepth is a wonderful resource!
English
Awesome work from @Jimantha and co., as always! One aspect of our AerialMD work that we’ve always felt was underrated is its potential to help “metricize” everything through geotagged image registration. It’s great to see that vision being pushed further and executed nicely here. Congrats on the nice work @ambie_kk!
Yuanbo Xiangli@ambie_kk
Honey, I Shrunk the Arc de Triomphe! 😱 Ever notice how SOTA depth models suffer from "scale-collapse"—metrically shrinking distant landmarks like they're toys? We introduce MetricScenes: a new in-the-wild metric dataset that fixes this!
English
Noah Snavely retweetledi
Excited to share ArchSym at #CVPR2026! 🏛️
Existing 3D symmetry detectors work well on clean, object-centric data. But what about in the wild?
In our work, we tackle 3D-grounded reflectional symmetry detection specifically for real-world architectural landmarks.
🧵[1/7]
English
Noah Snavely retweetledi
Honey, I Shrunk the Arc de Triomphe! 😱
Ever notice how SOTA depth models suffer from "scale-collapse"—metrically shrinking distant landmarks like they're toys? We introduce MetricScenes: a new in-the-wild metric dataset that fixes this!
English
A really nice paper with a really cool title from Yuanbo, Hanyu, and Xueqing!
Yuanbo Xiangli@ambie_kk
Honey, I Shrunk the Arc de Triomphe! 😱 Ever notice how SOTA depth models suffer from "scale-collapse"—metrically shrinking distant landmarks like they're toys? We introduce MetricScenes: a new in-the-wild metric dataset that fixes this!
English
Noah Snavely retweetledi
This work has been fully open-sourced, including all code, model weights, and data related scripts. Feel free to check it out!
Our CVPR poster session will be on Saturday, June 6, from 4:45 to 6:45 PM in ExHall A & F 2. Our team (@holynski_, @jon_barron , @ChrisWu6080, @Jimantha, and me) would be onsite and very happy to discuss it in person!
Haian Jin@Haian_Jin
Spatial reconstruction is a long-context problem: real scenes come with hundreds of images. But O(N²) transformer-based models don’t scale efficiently. Introducing: 🤐ZipMap (CVPR ’26): Linear-Time, Stateful 3D Reconstruction via Test-Time Training (TTT). ZipMap “zips” a large image collection into an implicit TTT scene state in a single linear-time operation. The state will then be decoded into spatial outputs, and can be queried efficiently for novel-view geometry and appearance (~100 FPS) ZipMap is not only much faster (>20× faster than VGGT), but also matches or surpasses the accuracy of all SOTA models.
English
Noah Snavely retweetledi
Humans can watch tasks like cooking or assembly and reason about what happened, when, and between which parts. Can LVLMs do the same? We built Flat-Pack Bench to test this – and found there is still a long way to go. Accepted at #CVPR2026! 🎥🪑🧩(1/n)
GIF
English
Noah Snavely retweetledi
Feed-forward 3D reconstruction methods typically predict pointmaps in camera-centric frames. But why should a camera's arbitrary orientation define the coordinate system?
We introduce G3T, a transformer that predicts pointmaps in gravity-aligned frames. Regardless of input image orientation, our method always produces upright pointmaps (see demo).
We leverage this uprightness to create G3T-Long, a submap-based reconstruction method that improves robustness on long-sequence 3D reconstruction (more on that below).
Interactive demos, code, and model weights are available on our project page.
English