Vasilis Belagiannis

Professor at @UniFAU. Past: Univ. Magdeburg, Ulm Univ., VGG Oxford University, TU München + Industry. personal account.

[Vasilis Belagiannis @bazile]

🔥 Invited Speakers: David Forsyth, Danica Kragic, Josef Kittler, Olga Russakovsky, & Jean Ponce!

[Vasilis Belagiannis @bazile]

CfP: Join us for the 3rd Workshop on More Exploration, Less Exploitation (MELEX 2026) at #ECCV2026 (@eccvconf ) in Malmö! 🇸🇪
Tired of minor SOTA-chasing tweaks? We are looking for bold, highly innovative and exploratory computer vision ideas! (1/3)

[Vasilis Belagiannis @bazile]

Submission Deadline: June 22, 2026 ⏰
Accepted papers will be published in the ECCV proceedings.

Submit your manuscript + 1-page review response letter here: 🔗 https://t.co/Md6jBB1wI2 (2/3)

#ComputerVision #MachineLearning #ECCV #DeepLearning

[Vasilis Belagiannis @bazile]

@abursuc Note that our MELEX workshop is taking place again this year with related highly inspirational talks! MELEX 2026 @ #ECVV2026 https://t.co/8WHnBawpXl

[Marcel B. @marcel_butucea]

Turns out you can edit images with a VQ‑VAE autoregressive model faster than diffusion – they “nudge” the logits using a mask from the source token map. Same quality, ~10× speedup. Who knew a little logit push could beat diffusion? 🚀🤯

https://t.co/jxqzFVq8sM

[International Conference on 3D Vision (3DV) @3DVconf]

Just as we say goodbye to Vancouver (YVR)🇨🇦🥹, it’s time to reveal our next destination! ✈️

From the Pacific coast to the Mediterranean sea...
We are thrilled to announce that #3DV2027 is heading to Thessaloniki, Greece (SKG)! 🇬🇷🥳

See you there in Mid-April 2027! 🌍

[Yuki @y_m_asano]

[new CVPR'26 paper]
🔄 SSL works great when you have tons of data.
But in 3D… we don’t.
High-quality 3D scans are expensive, slow, and hard to scale. So what if we could pretrain 3D models without any real 3D scans? 1/

[Ken Goldberg @Ken_Goldberg]

The @IEEE Transactions on Robot Learning (T-RL) will launch on March 30! Co-EiCs: Todd Murphey and Vincent Vanhoucke
https://t.co/v8bRowWtHr

[Computer Vision and Pattern Recognition Papers @CSVisionPapers]

GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection

Yutong Yang, Katarina Popović, Julian Wiederer, Markus Braun, Vasileios Belagiannis, Bin Yang
https://t.co/uM0P0SZ55F [𝚌𝚜.𝙲𝚅]

[Computer Vision and Pattern Recognition Papers @CSVisionPapers]

ProGiDiff: Prompt-Guided Diffusion-Based Medical Image Segmentation

Yuan Lin, Murong Xu, Marc Hölle, Chinmay Prabhakar, Andreas Maier, Vasileios Belagiannis, Bjoern Menze, Suprosanna Shit
https://t.co/tOTdinrP8C [𝚌𝚜.𝙲𝚅]

[Transactions on Machine Learning Research @TmlrOrg]

📣 Heads-up 📣 As in previous years, TMLR will pause new submissions over the upcoming holiday period from December 2 2025 to January 5 2026 (midnight AOE on both dates). We will resume accepting new submissions on January 6, 2026. Happy Holidays!

[Accepted papers at TMLR @TmlrPub]

Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curva...

Rohan Asthana, Joschua Conrad, Maurits Ortmanns, Vasileios Belagiannis.

Action editor: Frederic Sala.

https://t.co/7g3MlSzOr8

#cnn #benchmarks #netw

[Yuki @y_m_asano]

Today we release Franca, a new vision Foundation Model that matches and sometimes outperforms DINOv2.
The data, the training code and the model weights (with intermediate checkpoints) are open-source, allowing everyone to build on this.

Methodologically, we introduce two new SSL components, one is a multi-granularity SK clustering loss that utilizes Matryoshka representations and a quick post-pretraining scheme to remove unwanted spatial biases.

This is the result of a close and fun collaboration @valeoai (in France) and @FunAILab (in Franconia)

[Vasilis Belagiannis @bazile]

Dive into the details and code:
📖 https://t.co/DGAPp5z5Qt (paper)
🖨️ https://t.co/C3aGFqjIKH (pre-print)
💾 https://t.co/801BVSQ0cy (code)

#FAU #DFG #MachineLearning #ComputerVision

[Vasilis Belagiannis @bazile]

“Revisiting Gradient-Based Uncertainty for Monocular Depth Estimation” IEEE TPAMI, is here! We present a further formulation of our gradient-based method for quantifying #uncertainty in monocular #depth predictions #NoTrainingNeeded.
Joint work between @UniFAU & @uni_ulm
Links⬇️

[Minhyuk Sung @MinhyukSung]

A huge thank you to Jiaming Song (@baaadas) for delivering a wonderful guest lecture in our "Diffusion Models and Applications" course! He shared valuable insights on video generative models and the future of generative AI.

🎥 https://t.co/uHylRlUN4H
📚 https://t.co/LRZPwLulHw

[Vasilis Belagiannis @bazile]

Visual results

[Vasilis Belagiannis @bazile]

🎉🎄New WACV 2025 Publication!

"Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation" by Michele De Vita, Vasileios Belagiannis @UniFAU

We're excited to introduce one of the first uncertainty estimation methods for diffusion models!

Details below.

[Vasilis Belagiannis @bazile]

Results: Extensive evaluation on ImageNet and CIFAR-10 datasets shows superior performance in filtering low-quality samples and improving generation quality.

Paper: https://t.co/brctU7o2OG
Code: https://t.co/Qg3I6zG1a4

#FAU #MachineLearning #ComputerVision #DiffusionModels

[Vasilis Belagiannis @bazile]

🎉🎄New WACV 2025 Publication!

"Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation" by Michele De Vita, Vasileios Belagiannis @UniFAU

We're excited to introduce one of the first uncertainty estimation methods for diffusion models!

Details below.

[Vasilis Belagiannis @bazile]

💡 Theoretical Insights: We show that our uncertainty estimates are related to the second-order derivative of the diffusion noise distribution, providing a solid mathematical foundation.