Dive into the details and code:
📖 lnkd.in/d4FjwFY7 (paper)
🖨️ lnkd.in/dkdabrZ9 (pre-print)
💾 lnkd.in/dfnUk8-C (code)

#FAU #DFG #MachineLearning #ComputerVision

“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 @fau.de & @uniulm.bsky.social.
Links below.

Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.

Interesting, it appears the #ICCV2025 submission and supplementary materials deadlines are the SAME.

Visual results

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

📄 Paper: lnkd.in/d7JBSkiz
💻 Code: lnkd.in/dqFbC2nP

Online demo coming soon!
#FAU #MachineLearning #ComputerVision #DiffusionModels #WACV2025

💡 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.

🎯 Guided sampling: We use uncertainty estimates to drive the sampling process towards higher quality generations, resulting in improved FID results and fewer artefacts.

Key highlights:

📊 Training-free uncertainty: Our method estimates pixel-wise aleatoric uncertainty during the sampling phase without requiring any model modifications or additional training, allowing to filter out low quality samples.

🎉 🎄 New WACV 2025 Publication!

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

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

Links & highlights below