Nina Shvetsova

@ninashv__

PhD student at the University of Tübingen. Computer vision, video understanding, multimodal learning.

ninatu.github.io

Joined June 2021

Replies Reposts Media

Nina Shvetsova
@ninashv__
Mar 20
Presenting M2SVid at #3DV2026 today! We tackle Monocular-to-Stereo Video conversion using a end-to-end inpainting and refinement pipeline. 📍 Poster Session 1 (10:15 - 12:00) 🚀 Code and models are now released! 🔗 m2svid.github.io 💻 github.com/google-researc… @3DVconf
1
Nina Shvetsova
@ninashv__
Dec 16, 2025
Excited to share our new paper: M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion! ACCEPTED by 3DV 2026!🎬 👉 Project: m2svid.github.io 📄 Paper: arxiv.org/abs/2505.16565 Done with Goutam Bhat, @prunetruong, @HildeKuehne, @fedassa 🧵👇
1
Nina Shvetsova
@ninashv__
Aug 8, 2025
🚀 UTD is now fully released! Code ✅ Models ✅ 2M video descriptions ✅ Debiased splits for 12 datasets ✅ Everything you need to benchmark video models more fairly is now public: 🔗 github.com/ninatu/utd-pro… 🎥 Let’s make video understanding actually about video understanding.
1
Nina Shvetsova
@ninashv__
Jun 15, 2025
Check out our @CVPR poster!🎉 🕓 June 15, 4–6 PM 🖼️ Poster #278 | 📍ExHall D Unbiasing through Textual Descriptions — we address representation bias in video benchmarks, releasing debiased splits for 12 datasets! Can’t present in person due to visa issues, but I’ll be online! 💻
2
Nina Shvetsova
@ninashv__
Apr 29, 2025
🚀Excited to announce our @CVPR 2025 paper: Unbiasing through Textual Descriptions! We release UTD-descriptions for 1.9M videos and object-debiased splits for 12 datasets! 🔗Project: utd-project.github.io @NagraniArsha Bernt Schiele @HildeKuehne Christian Rupprecht 🧵👇
1