🚨 New drop: PartCrafter 🧩 A 3D-native DiT that generates 3D objects in parts 👉 wgsxm.github.io/projects/partc… The most exciting part for me: 🌟 We realised most 3D datasets already come with part-structured meshes — but previous works just ignored that. 🤯 Simple & Effective 🚀

PartCrafter Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

ByteDance and Carnegie Mellon researchers just announced PartCrafter This AI turns a single photo into fully editable 3D parts in seconds 10 wild examples:

💥 We just open-sourced the inference & training code of PartCrafter 🧩 — along with pretrained checkpoints! 🚀 Check it out here 👉 wgsxm.github.io/projects/partc… ❗️❗️ #OpenSource #3D #Diffusion #AI #PartCrafter

We just found a wonderful Huggingface🤗 space demo for 🧩PartCrafter made by Alex Nasa. Thank you very much🤩 !!! If you'd like to generate 3D objects in parts, try it out! It's super simple & fast & free: huggingface.co/spaces/alexnas…

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second Chenguo Lin, Yuchen Lin, Panwang Pan, Mark Yu, Honglei Yan, Katerina Fragkiadaki, Yadong Mu tl;dr: dynamic splatter pixels->renderable deforming 3D particles->3D dynamic scenes arxiv.org/abs/2507.10065

MoVieS Motion-Aware 4D Dynamic View Synthesis in One Second

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second

"🎞️MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second" TL;DR: Feed-forward framework that jointly reconstructs appearance, geometry and motion for 4D scene perception from monocular videos in one second.

Just found a great product-ready implementation of our PartCrafter (wgsxm.github.io/projects/partc…) 🤩 Can't wait to try it!

🧩 PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers 📐 Jupyter Notebook 🥳 Thanks to Yuchen Lin ❤ Chenguo Lin ❤ Panwang Pan ❤ Honglei Yan ❤ Yiqiang Feng ❤ Yadong Mu ❤ Katerina Fragkiadaki ❤ Thanks to Alex Nasa ❤

"Generate in Parts" is so insanely good, it even generated the bullets inside the cylinder - automatically, from a single image. Every part comes cleanly separated: barrel, cylinder, trigger, hammer, etc… The future of 3D AI goes live next week on app.scenario.com 🔥

Beyond thrilled to officially roll out "Generate in Parts" on app.scenario.com - a new standard for Image-to-3D workflows! Say goodbye to monolithic Al meshes, and hello to clean, modular 3D assets you can animate, edit, or 3D print. Let's dive in with #PartCrafter👇!

Preprint of (not) today: Lin and Lin et al., "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second" -- chenguolin.github.io/projects/MoVie… Feed-forward VGGT + Splats/Motion estimation heads, trained also with rendering & motion estimation losses. Multitask training improves all.

"Generate in Parts" just got better with "Split in Parts"! 🥹😇 Hervé Nivon added a toggle in the Scenario 3D viewer that instantly splits generated meshes into an exploded view. See how PartCrafted breaks down your model - no need to download and check in Blender anymore.

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

Comfy3D Update: (v0.1.6) - Integrated PartCrafter (Both object & scene mode) - A bunch of UX fixing ML Devs: Denis camenduru github.com/MrForExample/C… 田中義弘 | taziku CEO / AI × Creative -Zho- toyxyz Robin Huang ComfyUI Neuro

Sunday morning reading … flight delay edition 😬