Jianyuan Wang 王建元

VGGT-Ω was selected as a Best Paper Finalist (15/16092) at CVPR 2026!

Excited to share VGGT-Ω, my last PhD paper and our strongest feed-forward 3D reconstruction model yet, including our explorations on how to use it for VLA and text alignment! Explore the project page, paper, code, and demo.

DINOv3 is out! Check out the blog post for amazing visuals, and enjoy the code!

VGGT was selected for the Best Paper Award (1/13008) at CVPR 2025! Try our model with the Hugging Face demo.

VGGT-Ω

Jianyuan Wang, Minghao Chen, Shangzhan Zhang, Nikita Karaev, Johannes Schönberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht

CVPR, 2026 (Best Paper Finalist)

[Paper] [Code] [Project Page] [🤗 Demo] [Model]

VGGT: Visual Geometry Grounded Transformer

Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, David Novotny

CVPR, 2025 (Best Paper Award)

[Paper] [Code] [Project Page] [🤗 Demo] [Twitter] [Slides]

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Jianyuan Wang, Nikita Karaev, Christian Rupprecht, and David Novotny

CVPR, 2024 (Highlight)

[Paper] [Project Page] [Code] [🤗 Demo]

DINOv3

Oriane Siméoni, Huy V Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski

[Paper] [Project Page] [Code]

CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos

Nikita Karaev, Iurii Makarov, Jianyuan Wang, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht

[Paper] [Project Page] [Code] [🤗 Demo]

Conference Reviewer for CVPR, ICCV, ECCV, ICLR, NeurIPS, and Journal Reviewer for TPAMI.