Try the early preview of 3D mesh segmentation. Assistant now separates generated assets into individual parts, giving you full control to add behaviors, customize materials & textures, or swap pieces. Soon, you'll even be able to segment imported models. https://t.co/Zy10Z2mfUW
👋Introducing CubePart, our new work on part-controllable 3D generation from Roblox (to appear in SIGGRAPH later this year).
CubePart generates semantically decomposed 3D assets directly from: a text prompt + a user-defined part schema.
This enables generated assets to plug directly into downstream animations, physics, and game-engine workflows.
CubePart relies on strong text-to-3D pre-training to generalize to open-vocabulary part schemas. This rich semantic backbone allows it to flexibly generate coherent parts for previously unseen schemas.
🌐Project page: https://t.co/PpxAbRFBf0
💻Code: https://t.co/VEGATV1B8t
📜Paper: https://t.co/7tkxbfJFMk
🗞️Blog post: https://t.co/roYIxKVUnN
@AvaLovelace0@RuixuanLiu_@RamananDeva@ChangliuL@junyanz89 If you miss the talk or want to dive deeper, please also check out our poster and our interview!
Poster Session Details:
- Location: Exhibit Hall I #306
- Time: Wed 22 Oct 2:45 p.m. HST — 4:45 p.m
Read the interview in ICCV Daily:
https://t.co/K791u7scoo
🏆 Excited to share that BrickGPT (https://t.co/yvi8cyrArX) received the ICCV Best Paper Award!
Our first author, @AvaLovelace0, will present it from 1:30 to 1:45 p.m. today in Exhibit Hall III.
Huge thanks to all the co-authors @RuixuanLiu_@RamananDeva@ChangliuL@junyanz89
We've released the code for LegoGPT. This autoregressive model generates physically stable and buildable designs from text prompts, by integrating physics laws and assembly constraints into LLM training and inference.
This work is led by PhD students @AvaLovelace0, @kangle_deng, @RuixuanLiu_, and in collaboration with CMU faculty Changliu Liu and Deva Ramanan.
LegoGPT is a small first step towards the ultimate goal of generative manufacturing of physical objects. Our implementation is limited to 20x20x20 dimensions, 21 object categories, and simple brick types, but we are working on scaling it up!
Code: https://t.co/4S3FaaRy6i
Website: https://t.co/796q4tmiiB
Demo: https://t.co/mZvnL0Km5M
We shared some early work towards a multi-modal and multi-task 3D foundation model at Roblox.
First release is a discrete shape tokenizer compatible with autoregressive modeling for text-to-shape. More to come soon
Github: https://t.co/MGjN0Hvbyv
Arxiv: https://t.co/jje6nYVquw
🚀 Introducing NormalFlow: the state-of-the-art tactile tracking algorithm! Just by touch 👇, it precisely tracks objects—even with minimal texture—and can even reconstruct objects! 🌟
project page: https://t.co/exvt2MFfya
paper (RA-L): https://t.co/fIZ3JLZAyN
⬇️(1/4)
3D content creation with touch!
We exploit tactile sensing to enhance geometric details for text- and image-to-3D generation.
Check out our #NeurIPS2024 work on Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation: https://t.co/QyW1TkdvSo
1/3
[2/2]
Joint work w/ Tim Omernick, Alex Weiss, @RamananDeva, @junyanz89, @TinghuiZhou, and @magrawala 📚
Part of this work has been incorporated into @Roblox Studio's AI texturing. 🖌️🤖
Code has been released: https://t.co/QK7iDU8MGv 🧑💻
[1/2]
📢 I'll present "FlashTex: Fast Relightable Mesh Texturing with LightControlNet" at #ECCV2024’s Oral Session tomorrow! 🎉
Join me to explore how our generated textures can be properly relit in various lighting environments. ⚡
📅 Oral: Tue, Oct 1st, 2 PM
📍 Poster: #159