Rendering a gaussian splat video from the nerfstudio viewer! This only took 2 minutes to render, which is about 20x faster than rendering the NeRF version. Impasse Louise-Émilie de la Tour d´Auvergne, Paris captured with the Insta360 RS 1". #NeRF #gaussiansplatting

MVDream: Multi-view Diffusion for 3D Generation paper page: huggingface.co/papers/2308.16… propose MVDream, a multi-view diffusion model that is able to generate geometrically consistent multi-view images from a given text prompt. By leveraging image diffusion models pre-trained on

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

Combine Google Maps 3d tiles and Luma gaussian splat scans via A-Frame / Three.js for high fidelity at tiny scale AND zoomable out to city scale all in the browser. 🙏 🎏Glitch hosting, PlayCanvas splat editing, NYTimes R&D 3dtiles component maps-and-splats.glitch.me

Code dropped: VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction Project: vastgaussian.github.io Code: github.com/kangpeilun/Vas…

😲 LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control 🤯 Jupyter Notebook 🥳 Thanks to Jianzhu Guo ❤ Dingyun Zhang ❤ Xiaoqiang Liu ❤ Zhizhou Zhong ❤ Yuan Zhang ❤ Pengfei Wan ❤ Di Zhang ❤ 🍊jupyter: please try it 🐣 github.com/camenduru/Live…

Microsoft released Trellis! Trellis is a new 3D model that generates high-quality 3D assets in formats like Radiance Fields, 3D Gaussians, and meshes.

I had a bit of fun with Microsoft Trellis this weekend. All assets are generated via Trellis (based on Flux gen. images). The layout, lighting, shading and rendering in #b3d. Music: SUNOAI Models are not perfect at all, but usable through stylization, and a lot of DOF.

This is a timelapse of the 3D Gradient Texturing process. This time, I focused on texturing each UV section of the color gradient column separately for each corresponding part of the model's color 🎨 #wip #3dArt #timelapse #speedmodeling x.com/Sr_Jueves3D/st…

Boom! We cracked it! Today we are introducing Boomless Cruise—supersonic flights up to 50% faster with no audible sonic boom. We quietly (har har) demo'd this on XB-1's first supersonic flight—three times actually. 🧵👇

I've made a few nice tests with Wan2.1 image to video 480p in Comfyui. I don’t fully understand how to control the camera or character motion, but its quite nice to see them move! I've been able to generate up to 65 frames and 768p resolution.

Introducing Mistral Small 3.1. Multimodal, Apache 2.0, outperforms Gemma 3 and GPT 4o-mini. mistral.ai/news/mistral-s…

I was doing a demo at Midas on VACE and was asked if we could make a thing burn, and it failed miserably😅. One thing is to make a thing burn, the other is how do you control placement, flow and look of that fire. So spend a few late nights tinkering...

Microsoft just released TRELLIS 2