Nina Shvetsova

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

[Nina Shvetsova @ninashv__]

@sidgairo18 Congrats!!!

[Michael Black @Michael_J_Black]

NeuralFur wins Best Paper Runner Up at @3DVconf. From multi-view images, we create a strand-based hair groom for animals. Unlike human hair, fur varies in length across the body parts of animals.
NeuralFur leverages a VQA approach to infer fur lengths and directions across the body and to create a furless mesh.
We then reconstruct strand-based fur geometry from multi-view images, resulting in a realistic animal model that is ready for physics-based animation in game engines like Unreal.
Code is online. Check out the project page link below.

Congratulations to @ness_pirs @bernakabadayi @AYiannakidis @gfgbec and @JustusThies!

https://t.co/Xj6MV220e0

[Michael Niemeyer @Mi_Niemeyer]

Excited and deeply honored to receive the #3D Outstanding Doctoral Dissertation Award! 🏆 Huge thanks to the awards committee and to everyone making 3DV such a blast.
And I couldn't be happier to share this recognition with my long-time friend and colleague @songyoupeng 🙌✨

[Nina Shvetsova @ninashv__]

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!

🔗 https://t.co/PibIzp5RzI
💻 https://t.co/6ZkHc2C7dg…
@3DVconf

[WiCV @WiCVworkshop]

🚨Call for Extended Abstracts for the WiCV Women in Computer Vision workshop at @CVPR 2026.

Find all the details at: https://t.co/VdKr6mdVnU

Submission Portal: https://t.co/8HfFUtzQ6c

Deadline: 24 March 2026

#CVPR2026 #WiCV #ComputerVision

[Hilde Kuehne @HildeKuehne]

🎆 Wrapping up 2025 with a review of some exciting papers from our group 🎊 covering everything across audio-visual learning, explainability, bias mitigation & video understanding 🧵⬇️

[Nina Shvetsova @ninashv__]

🔗 Check it out:
👉 Project: https://t.co/sLgaM9of9n
📄 Paper: https://t.co/b8yPeyociQ
💻 Code: (coming soon!)

@3DVconf

[Nina Shvetsova @ninashv__]

Excited to share our new paper: M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion! ACCEPTED by 3DV 2026!🎬

👉 Project: https://t.co/sLgaM9oMYV
📄 Paper: https://t.co/b8yPeyoK8o

Done with Goutam Bhat, @prunetruong, @HildeKuehne, @fedassa 🧵👇

[Nina Shvetsova @ninashv__]

📊 Results:

✅Higher Quality: Our approach outperforms previous state-of-the-art methods, being ranked best 2.6x more often than the second-place method in user studies.
✅Faster: Runs 6x faster than state-of-the-art competitors.

[WiCV @WiCVworkshop]

🌟Join us for the keynote with @HildeKuehne
on 19th October, 1:55 pm at the WiCV workshop in Honolulu!
#WiCV #WomeninComputerVision #ICCV2025

@ICCVConference

[Ragav Sachdeva @RagavSachdeva]

🚨🚨🚨Deadline <10 days 🚨🚨🚨

Submit your extended abstracts on AI driven comic analysis to the COMIQ workshop #ICCV2025

https://t.co/zrvIB1qr4D

[Nina Shvetsova @ninashv__]

@edsonroteia Thanks! ❤️

[Nina Shvetsova @ninashv__]

🚀 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:
🔗 https://t.co/rA88ztIZJs
🎥 Let’s make video understanding actually about video understanding.

[Jan Eric Lenssen @janericlenssen]

Can diffusion models solve visual Sudoku?

If you are at #ICML2025, come to our poster in the Wednesday morning poster session (Poster Session 3 East, Poster 3412) and find out!

@ChrisWewer @bartek_pog Bernt Schiele @janericlenssen

[Nina Shvetsova @ninashv__]

🔗 Paper: https://t.co/PVjGVYlHjr
🔗 Project: https://t.co/RsDXmwRl4Y
🔗 Code & models: https://t.co/rA88ztIZJs (coming soon!)

Done with @NagraniArsha Bernt Schiele @HildeKuehne Christian Rupprecht

[Nina Shvetsova @ninashv__]

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! 💻