Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input... text. That is, text --> 4D! Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data. Paper: Website:show more

Text-To-4D Dynamic Scene Generation Presents MAV3D (Make-A-Video3D), a method... for generating three-dimensional dynamic scenes from text descriptions. proj: abs:show more

✨ Any static 3D assets ➡️ 4D dynamic worlds.... Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs. It generalizes surprisingly well across a wide range of objects 🤯 and can even be used to learn robotics manipulation policy 🤖! Project page: Dive deeper in a 🧵: 1/nshow more

Beyond text. Beyond static data. Today, Adaptive Data is... now multimodal. Bringing advanced data optimization to image datasets. Data built the last generation of AI. Adaptive Data is building the next.show more

Progressive Rendering Distillation released on Hugging Face Adapting Stable... Diffusion for Instant Text-to-Mesh Generation without 3D Datashow more

Vedal reveals Neuro's 3d training data

Introducing Objaverse, a massive open dataset of text-paired 3D... objects! Nearly 1 million annotated 3D objects to pave the way to build incredible large-scale 3D generative models: 🧵👇 🤗 Hugging Face: 📝ArXiv: #CVPR2023show more

This is such a cool interactive website to learn... how LLMs work. It’s combines step-by-step text explanations with dynamic 3D visualizations for an immersive learning experience. Available to everyone for free!show more

How to condense data headers with this text formatting... hack. 🤩show more

Google presents LayoutVLM a model that can generate 3D... layouts from text instructionsshow more

Soon anybody can be animated everywhere! En3D can generating... 3D humans either from text or images and animate them!show more

Roblox just casually dropped a app for Cube 3D... on Hugging Face generates 3D models directly from textshow more

🤖 Pika: Fast Data Collector Solution for Embodied Intelligence... 2-step clamp action = instant power-on! Zero lag, ultra-synced moves. Featherlight design captures dynamic data like your morning latte. Train AI faster—no clunky gear! ⚡ #Robotics #AI #data #VLA #LLMs #RobotArmshow more

It’s never been easier for 3D animators to bring... their creative vision to life. This is motion capture powered by AI. No suits or markers needed. You can now capture multiple people anywhere using standard cameras, and Move AI will generate 3D motion data from the 2D video.show more

A data-driven FDA. No shortcuts. No rubber stamps.

AI runs on data. but most of it is... stale, outdated, static. what if intelligence was powered by living signals from real human activity? introducing: 𝐳𝐃𝐚𝐭𝐚 - the Data Layer Powering Zentry and The AI Data Economy ⇢show more

NVIDIA introduces Edify 3D AI model You can generate... high quality 3D assets from text or image input under 2 minutes! With PBR materials, quad-mesh topologies, and 4k textures. 6 wild examples:show more

This is hand and finger motion capture powered by... AI. 3D motion data is generated from 2D video. No suits or gloves required. This example was captured using Move Multi-Cam with 8 GoPro cameras shooting at 4K and 120 FPS.show more