We are presenting Dual Point Maps as a #CVPR highlight tomorrow! Learn about our novel, data-efficient representation for 3D/4D deformable objects—an alternative to classical template shape models. 📍🕑 ExHall D, Poster #100, afternoon session 🌍 dualpm.github.io Brief explanation 👇

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

Jensen (Jinghao), Zhou, Hang Gao, Vikram Voleti, Aaryaman Vasishta, Chun-Han Yao, Mark Boss, Philip Torr, Christian Rupprecht, Varun Jampani Stable Virtual Camera: Generative View Synthesis with Diffusion Models https://arxiv.org/abs/2503.14489

Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi SHIC: Shape-Image Correspondences with no Keypoint Supervision https://arxiv.org/abs/2407.18907

Nikita Karaev, Iurii Makarov, Jianyuan Wang, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos https://arxiv.org/abs/2410.11831

Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, David Novotny: VGGT: Visual Geometry Grounded Transformer https://arxiv.org/abs/2503.11651 https://arxiv.org/pdf/2503.11651 https://arxiv.org/html/2503.11651

Raza Yunus, Jan Eric Lenssen, Michael Niemeyer, Yiyi Liao, Christian Rupprecht, Christian Theobalt, Gerard Pons-Moll, Jia-Bin Huang, Vladislav Golyanik, Eddy Ilg Recent Trends in 3D Reconstruction of General Non-Rigid Scenes https://arxiv.org/abs/2403.15064

Nikita Karaev, Ignacio Rocco, Benjamin Graham, Natalia Neverova, Andrea Vedaldi, Christian Rupprecht CoTracker: It is Better to Track Together https://arxiv.org/abs/2307.07635

VGGT: Visual Geometry Grounded Transformer ‪@jianyuanwang.bsky.social Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, David Novotny tl;dr: Mast3r meets CoTracker, overcomplete predictions (depth AND pointmap, etc).Training: 64A100x9days. Sota on IMC-2020. arxiv.org/abs/2503.11651

Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi Splatter Image: Ultra-Fast Single-View 3D Reconstruction. (arXiv:2312.13150v1 [cs.CV]) http://arxiv.org/abs/2312.13150

Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht, David Novotny VGGT: Visual Geometry Grounded Transformer https://arxiv.org/abs/2503.11651

VGGT: Visual Geometry Grounded Transformer @jianyuanwang.bsky.social, Minghao Chen, @nikkar.bsky.social, Andrea Vedaldi, Christian Rupprecht, David Novotny tl;dr:image->DINO->image tokens (w/ camera tokens)->frame-wise&global self attention->camera&DPT head->3D attributes arxiv.org/abs/2503.11651

Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi Learning segmentation from point trajectories https://arxiv.org/abs/2501.12392

Learning segmentation from point trajectories Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi tl;dr: long-term motion -> low-rank approximation -> segmentation -> profit. arxiv.org/abs/2501.12392

[New pre-training / augmentation dataset] MoireDB – a formula-generated interference-fringe image dataset for synthetic pre-training and data augmentation 🎉🎉🎉 Paper: arxiv.org/abs/2502.01490

📢 Paper accepted to #ICLR2025 🎉 "GSLoc: Efficient Camera Pose Refinement via 3D Gaussian Splatting" TL;DR: a novel test-time camera pose refinement framework leveraging 3DGS as the scene representation and MASt3R for 2D matching. 🔗: arxiv.org/abs/2408.11085

[2024-12-17] 📚 Updates in #SILM (1) Responsible AI Governance: A Response to UN Interim Report on Governing AI for Humanity 🔍 More at researchtrend.ai/communities/SILM

Oishi Deb, KR Prajwal, Andrew Zisserman New keypoint-based approach for recognising British Sign Language (BSL) from sequences https://arxiv.org/abs/2412.09475

Qianyi Deng, Oishi Deb, Amir Patel, Christian Rupprecht, Philip Torr, Niki Trigoni, Andrew Markham Towards Multi-Modal Animal Pose Estimation: An In-Depth Analysis https://arxiv.org/abs/2410.09312

NeurIPS2024 Work with Chuanxia Zheng, Weidi Xie and Andrew Zisserman Thank Andrew for editing the poster! Thank you for coming over to our poster and interest in our work!

I'm building a new research lab @ Uni of Cambridge focusing on 4D computer vision and generative models. Interested in joining us as a PhD student? Apply to the Engineering program by Dec 3 🗓️ www.postgraduate.study.cam.ac.uk/courses/dire... ChatGPT's "portrait of my current life"👇 elliottwu.com