Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis dynamic3dgaussians.github.io We model the world as a set of 3D Gaussians that move & rotate over time. This extends Gaussian Splatting to dynamic scenes, with accurate novel-view synthesis and dense 3D trajectories.

step back until you see it... #aiart #sdxl

Video rendering in its reconstructed space 🙂 Using camera pose estimation/photogrammetry we render videos (here in the middle) in its own reconstructed world (using only the video as input). Wait for #GaussianSplatting ...! Try : whenistheweekend.com/k/snow.html (Check camPov and Play)

Great article about Gaussian Splatting by dylan explaining simply but in depth what gaussian splatting are and why they are taking over huggingface.co/blog/gaussian-…

Tired of watermarks in videos? ProPainter is a new AI video inpainting method that is able to remove objects, complete masked videos, remove watermarks and even supports video outpainting 🤯 shangchenzhou.com/projects/ProPa…

Introducing "Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis". TL;DR: Novel views of faces at ultra-high 4K resolution from very few input images. Google AR & VR ETH Zurich AIT Lab #ICCV2023. syntec-research.github.io/Preface/ See thread below.

I am probably the last person to do this tutorial - everyone did this a while ago - but no matter; Consistent characters in MidJourney and SD It's quite useful! 🧵

3D Gaussian Splats use case? We changed the opening scene of 'The Shining' after 43 years😮 Cut the scene, train the gaussians, take it to Unreal Engine and after that the possibilities are endless. Watch the entire experiment on our channel Bad Decisions Studio.

3D Gaussian Splatting with Unity VFX Graph github.com/keijiro/SplatV…

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: huggingface.co/papers/2310.16… present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D

The possibilities of AI video editing are gonna be nuts! Just this week, 10 different papers got released, that show us a glimpse of the future. Let's take a look at what awaits us:

(1/2) Check out "FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models"! We synthesize high-fidelity motion sequences of neural parametric head models from audio input. Works with music and various languages :) youtu.be/7Jf0kawrA3Q shivangi-aneja.github.io/projects/facet…

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy

Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.

An example of how DUSt3R can do "impossible matching": given two images without any shared visual content (my office, obviously never seen at training), it can output an accurate reconstruction (no intrinsics, no poses!) in seconds

MARTIN SCORSESE obsessing over the framing of a shot. One of the things that makes him a great filmmaker.

GitHub: github.com/henry123-boy/S…

We’re announcing a research collaboration with Commonwealth Fusion Systems, one of the world’s leading nuclear fusion companies. Together, we’re helping speed up the development of clean, safe, limitless fusion power with AI. ⚛️

youtu.be/OIxuGF6CwnU?si…