Torben

11 posts

Torben

@PeterTor_

PostDoc @ETH

zurich Sumali Ağustos 2015

78 Sinusundan50 Mga Tagasunod

Torben@PeterTor_·14 Mar

Excited to introduce Thera🔥 Our method achieves SOTA in arbitrary-scale super resolution

Nando Metzger@NandoMetzger

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.

English

Torben nag-retweet

Dino Fuzi@DinoFuzi·24 Şub

CubeDiff talk today for those who are interested! 🚀

Ayça Takmaz@aycatakmaz

ZurichCV meet-up #8 is happening today, featuring Xi Wang (@xiwang1212) on egocentric learning & Nikolai Kalischek (@DinoFuzi) on diffusion-based panorama generation! 📍ETH Zurich OAT Floor 14 🗓️24 Feb 18:00 CET 📜zurichai.ch/events/zurichc… @zurichnlp

English

476

Torben@PeterTor_·8 Oca

@AntonObukhov1 makes sense they put it into a dedicated device, so its harder to stack them in a server rack. Also it looks a bit to small, compared to a 4090 etc 🤔

English

Anton Obukhov@AntonObukhov1·7 Oca

Whoa, 128GB for $3000? It seems 2025 is the year NVIDIA raises the bar on memory limits

NVIDIA@nvidia

Announcing NVIDIA Project DIGITS, a personal AI supercomputer that’s powered by the NVIDIA GB10 Superchip and based on #NVIDIAGraceBlackwell architecture. nvda.ws/4fLyTm3 Preconfigured with the NVIDIA AI software stack, developers, researchers, data scientists and students can prototype, fine-tune and inference large AI models on their desktop and deploy them to the data center or cloud. #CES2025

English

1.2K

Torben nag-retweet

Anton Obukhov@AntonObukhov1·19 Ara

Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you! Details 🧵

English

361

39.3K

Torben nag-retweet

Anton Obukhov@AntonObukhov1·2 Ara

Introducing 🛹 RollingDepth 🛹 — a universal monocular depth estimator for arbitrarily long videos! Our paper, “Video Depth without Video Models,” delivers exactly that, setting new standards in temporal consistency. Check out more details in the thread 🧵

English

106

636

49.8K

Torben nag-retweet

Anton Obukhov@AntonObukhov1·20 Ara

Marigold Depth got an update! 🖨️ Introducing a NEW 3D-printing demo feature! 🚀 Demo now 2x faster, with fine controls 🔓 Switched to Apache-2 license 💻 Code enhancements: fp16 & batched inference === 🤗 Demo: huggingface.co/spaces/toshas/… 🌐 Website: marigoldmonodepth.github.io

English

377

86.5K

Torben@PeterTor_·14 Ara

@Orwelian84 @Trolliacc1234 @DinoFuzi @JanDirkWegner1 We list it in the paper - Inference on the standard model is between 7.4 - 10 GB. Higher resolution costs more.

English

Atlas3D@Orwelian84·14 Ara

@Trolliacc1234 @DinoFuzi @PeterTor_ @JanDirkWegner1 probably 40-80 gb

English

Torben nag-retweet

Dino Fuzi@DinoFuzi·13 Ara

📢 Excited to share our latest work TetraDiffusion! TetraDiffusion generates highly detailed, textured 3D meshes in a matter of seconds. Project page: tetradiffusion.github.io Paper: arxiv.org/abs/2211.13220 In collaboration with @PeterTor_, @JanDirkWegner1 and K. Schindler

English

190

18.2K

Torben@PeterTor_·14 Ara

@davisblalock ChatGPT also loosens its tongue when drunk:

English

Davis Blalock@davisblalock·13 Ara

Here are all the ways to get around ChatGPT's safeguards: [1/n]

English

Torben@PeterTor_·26 Nis

@EEMLcommunity

GIF

QME

EEML@EEMLcommunity·25 Nis

EEML goes worldwide! We received 738 applications from 73 countries! The first round of notifications was released. **Those accepted, please confirm ASAP!** Tomorrow evening we release the final notifications. Fingers crossed!

GIF

English

Torben@PeterTor_·7 Kas

@DeepMindAI @Blizzard_Ent any plans to make it a competition like google ai challenges?

English

Tuklasin

@AntonObukhov1 @Orwelian84 @Trolliacc1234 @DinoFuzi @davisblalock @EEMLcommunity @DeepMindAI @Blizzard_Ent