Rodrigo Daudt retweeted
🤩 Thera, the first state-of-the-art model that allows super-resolution to arbitrary-scale !
App is live on @huggingface.
Rodrigo Daudt retweeted
We present Thera🔥: The new SOTA arbitrary-scale super-resolution method with built-in anti-aliasing. Our approach introduces Neural Heat Fields, which guarantee exact Gaussian filtering at any scale, enabling continuous image reconstruction without extra computational cost.
Rodrigo Daudt retweeted
Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
Alexander Becker (@A99529971), Rodrigo Caye Daudt (@rcdaudt), Dominik Narnhofer, Torben Peters (@PeterTor_), Me (@NandoMetzger), Jan Dirk Wegner, Konrad Schindler.
Rodrigo Daudt retweeted
thera
Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution
github.com/prs-eth/thera
Rodrigo Daudt retweeted
Researchers at @ETH_en have developed an AI-based solution that uses #satellite images to measure snow depth with a much better resolution than previous methods. Good news for me as a touring skier⛷️❄️🏔️! ethz.ch/en/news-and-events/e…
It’s great to see my work featured on ETH’s website, thank you!
AI + Satellites = accurate measurement of snow . 🛰❄
This provides winter sport enthusiasts or operators of hydropower plants with an indication of how certain they can be about the estimate of #SnowDepth across Switzerland.
brnw.ch/21wFiYu
@innosuisse @WSL_research
Rodrigo Daudt retweeted
Introducing Marigold 🌼 - a universal monocular depth estimator, delivering incredibly sharp predictions in the wild! Based on Stable Diffusion, it is trained with synthetic depth data only and excels in zero-shot adaptation to real-world imagery. Check it out:
🌐 Website: marigoldmonodepth.github.io/
🤗 Hugging Face Space: huggingface.co/spaces/toshas…
📄 Paper: arxiv.org/abs/2312.02145
👾 Code: github.com/prs-eth/marigold
The team: Bingxin Ke (@KBingxin), yours truly (@AntonObukhov1), Shengyu Huang (@ShengyHuang), Nando Metzger (@NandoMetzger), Rodrigo Caye Daudt (@rcdaudt), and Konrad Schindler.
#ComputerVision #PRS #ETHZurich
Rodrigo Daudt retweeted
Diffusion-Super-Resolution
[CVPR 2023] Guided Depth Super-Resolution by Deep Anisotropic Diffusion
github.com/prs-eth/Diffusion…
Rodrigo Daudt retweeted
Excited to announce that our paper "Guided Depth Super-Resolution by Deep Anisotropic Diffusion" has been accepted at CVPR 2023!🎉 You can check out the ArXiv preprint and code repository to learn more about the research. #CVPR2023 #SuperResolution
arxiv.org/abs/2211.11592
Rodrigo Daudt retweeted
Deadline in a week!
Consider submitting an abstract to our #EGU23 ML4Cryo session (CR2.5): meetingorganizer.copernicus.…
#cryosphere #MachineLearning #DeepLearning #remotesensing #earthobservation #naturalhazards #ice #snow #Avalanche
Rodrigo Daudt retweeted
Thanks for sharing! Big thanks to all of the involved people, especially @john_e_vargas @rcdaudt, Konrad Schindler, and @devistuia
Link to our paper:
nature.com/articles/s41598-0…