Malte Prinzler

PhD Student at MPI for Intelligent Systems Tübingen / ETH Zürich. Messing around with photo-realistic head avatars.

[Malte Prinzler @MaltePrinzler]

(1/5)
🚀 Excited to share our CVPR paper MATCH!
Website: https://t.co/pVkFpdk9Og
Given calibrated multi-view images, MATCH infers static Gaussian splat textures in correspondence across subjects and expressions. This speeds up avatar optimization by a factor of 10x.🧵👇

[Malte Prinzler @MaltePrinzler]

(5/5) 🙏 Huge shoutouts to my amazing co-authors at @ETH and @Google: Paulo Gotardo, @SiyuTang3 , and Timo Bolkart!

[Malte Prinzler @MaltePrinzler]

(1/5)
🚀 Excited to share our CVPR paper MATCH!
Website: https://t.co/pVkFpdk9Og
Given calibrated multi-view images, MATCH infers static Gaussian splat textures in correspondence across subjects and expressions. This speeds up avatar optimization by a factor of 10x.🧵👇

[Malte Prinzler @MaltePrinzler]

(4/5) 🛠️ What can it do?
✅ Photo-realistic 3D reconstruction
✅ Semantic editing (e.g. hair swapping)
✅ Expression transfer
✅ Speed up avatar optimization by a factor of 10x by avoiding optimization-based head tracking⚡

[Frano Rajič @franorajic]

1/4 🚀 We’re excited to release MVTracker (ICCV 2025 Oral), the first data-driven multi-view 3D point tracker. MVTracker tracks arbitrary 3D points across multiple cameras, handling occlusions and varied camera setups without per-sequence optimization.

[Malte Prinzler @MaltePrinzler]

📢Happy to announce that the code for Joker is now publicly available:
https://t.co/tznmzT1E8h

Including pretrained weights and interactive demos 🤓

Feel free to play around!

[Malte Prinzler @MaltePrinzler]

(1/5)
Excited to announce our latest project:

-> Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions <-

From one reference image we generate a 3D reconstruction with a novel extreme expression controlled with a 3DMM and text.

Webpage: https://t.co/FezDuL9ugQ

[Malte Prinzler @MaltePrinzler]

@mc_buehler @SIGGRAPHAsia Congrats on the really cool results!

[Marcel C. Buehler @mc_buehler]

A purely synthetic face prior can generalize to casual in-the-wild captures and stylized faces 🤯

I'm happy to share our @SIGGRAPHAsia paper “Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures.”

https://t.co/UPNMexPbRc

[Malte Prinzler @MaltePrinzler]

(5/5)
Our method Joker generalizes well to out-of-distribution examples like heavy make-up, statues, and CGI characters.

See our project page https://t.co/FezDuL9ugQ for more results.

[Malte Prinzler @MaltePrinzler]

(1/5)
Excited to announce our latest project:

-> Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions <-

From one reference image we generate a 3D reconstruction with a novel extreme expression controlled with a 3DMM and text.

Webpage: https://t.co/FezDuL9ugQ

[Malte Prinzler @MaltePrinzler]

(4/5)
For 3D distillation, we render a NeRF under several views, noise the renderings, and denoise them using our 2D prior. The results are used as a target to optimize the NeRF.

This procedure is repeated several times to converge against high-quality 3D reconstructions.

[Egor Zakharov @eozakharov]

ICCV poster/oral decisions are out, and this work got an oral! 🎉Congratulations to all the colleagues, Vanessa @ness_pirs, Jenya, Igor, Andreea @andreead_a, and Victor Lempitsky!

And what an excellent start for Vanessa's PhD! Looking forward to her presentation in Paris😊

[Egor Zakharov @eozakharov]

Happy to share our new paper on hair reconstruction that will appear at #ICCV2023, congrats to @ness_pirs and colleagues!

We produce a detailed and personalized strand-based hairstyle from the monocular video.
Project page: https://t.co/pXKVKt7rwk

More details in the thread 🧵

[Malte Prinzler @MaltePrinzler]

You want to chat about our #CVPR22 paper "Neural Head Avatars from Monocular RGB Videos"? Join me for our virtual poster session today at 10am CDT / 5pm CEST on Floor 2, Poster 1. https://t.co/xHpgKH2QWX

@GrassalPhilip Titus Leistner @Carsten_Rother @MattNiessner @JustusThies