icarus_code's profile picture.

icarus

@icarus_code

icarus reposted

DART can generate high-quality human motions in real-time, achieving over 300 frames per second on a single RTX 4090 GPU! It combines text inputs with spatial constraints, allowing for tasks like reaching waypoints and interacting with scenes. zkf1997.github.io/DART/


icarus reposted
miniapeur's tweet image.

icarus reposted

続き。Ledge Climbing & Pistol Attack お試し。物理リアクションを実装したとき、もしかしたらコレが出来るのでは、と思いつつ。実際に銃撃処理をしています。ダメージ部位やリアクション方向も、それなりに正確。ちょっと残酷?💦 #UnrealEngine5 #UE5 #GameDev #IndieDev #ゲーム制作 #OpenToWork


icarus reposted

🚀 Segment Anything Model 2 (SAM 2) is a foundation model from Meta, designed to address promptable visual segmentation in both images and videos. SAM 2 provides strong performance across a wide range of tasks and visual domains. Demo links 👇


icarus reposted

Is this real? Think again! DEGAS: Detailed Expressions on Full-Body Gaussian Avatars. Paper: arxiv.org/abs/2408.10588 Project: initialneil.github.io/DEGAS


icarus reposted

Love this, feel exactly the same way: "I'm tired of the complexity involved in hosting my side projects."

tom_doerr's tweet image. Love this, feel exactly the same way: "I'm tired of the complexity involved in hosting my side projects."

icarus reposted

llama multimodal chatbot in 3 lines of code

_akhaliq's tweet image. llama multimodal chatbot in 3 lines of code

icarus reposted

Apollo-7b by @AIatMeta It parsed a 24min video in just 33 seconds and found the two watch brands that appear! 🕓 Try it out yourself 👇

lucatac0's tweet image. Apollo-7b by @AIatMeta 

It parsed a 24min video in just 33 seconds and found the two watch brands that appear! 🕓

Try it out yourself 👇

icarus reposted

New "Meshtron" paper from Nvidia produces "artist-like" meshes from point clouds. This is huge for producing useable assets from scan data or text-to-model diffusion systems. Could even be a powerful retopo tool for artist modeling workflows. arxiv.org/abs/2412.09548


icarus reposted

Excited to announce ScanNet++ v2!🎉 @chandan__yes and @liuyuehcheng have been working tirelessly to bring: 🔹1006 high-fidelity 3D scans 🔹+ DSLR & iPhone captures 🔹+ rich semantics Elevating 3D scene understanding to the next level!🚀 w/ @MattNiessner kaldir.vc.in.tum.de/scannetpp


icarus reposted

Introducing ASAL: Automating the Search for Artificial Life with Foundation Models sakana.ai/asal/ Artificial Life (ALife) research holds key insights that can transform and accelerate progress in AI. By speeding up ALife discovery with AI, we accelerate our…


United States Trends

Loading...

Something went wrong.


Something went wrong.