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]

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=iYmA…

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!

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.

Project Genie is a @GoogleLabs experiment that lets you simulate dynamic worlds you can navigate in real time with Genie, our general-purpose world model. Today, we’re connecting Project Genie to nearly 20 years of Street View data from Google Maps — so you can now build interactive spaces based on real-world locations. Street View imagery in Project Genie is available now for places in the U.S., and will expand to more locales over time. #GoogleIO

Introducing: Long-Tail Internet Photo Reconstruction (CVPR’26) We go beyond densely captured imagery to train more general 3D foundation models for the long tail of noisy, sparse, incomplete Internet photo collections of 3D scenes. Yet, we face a data bottleneck: models need ground truth for these long-tail scenes, which classical SfM fails to provide. How do we bypass it? We break this bottleneck with two key contributions. First, we introduce MegaDepth-X, a large new dataset of scenes with high-quality 3D supervision. Second, we propose a new way to simulate difficult image sets for training. Project page: megadepth-x.github.io/

To bring generalist intelligent robots to the real world, we have to overcome the data scarcity problem. At Rhoda, we are solving it by reformulating robot policies as video generation. Today, we introduce the Direct Video-Action Model (DVA)

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.

Come see our talk on "Pocket Time-Lapse" at SIGGRAPH today at 4pm in the Image Representation, Editing, & Generation session! West Building, Rooms 118-120. With @zzigakovacic , @madhavaggar and @AbeDavis