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.
@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 🤔
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 🧵
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 🧵
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: https://t.co/ChuxwCpnog
🌐 Website: https://t.co/829gaLP0lt
@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.
📢 Excited to share our latest work TetraDiffusion!
TetraDiffusion generates highly detailed, textured 3D meshes in a matter of seconds.
Project page: https://t.co/6qUH4tNI4p
Paper: https://t.co/KC5qgHi7u5
In collaboration with @PeterTor_, @JanDirkWegner1 and K. Schindler