Research model that unifies 3D scene generation and reconstruction in a single pixel-space diffusion model.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
PixWorld is a research model from authors Sensen Gao, Zhaoqing Wang, Qihang Cao, Dongdong Yu, Changhu Wang and Jia-Wang Bian. It is described as a single end-to-end pixel-space diffusion model that handles both 3D scene generation and 3D reconstruction, instead of working in a latent space.\n\nThe project page shows results for 3D reconstruction, image-to-3D generation and text-to-3D generation. It includes comparisons with baselines, a gallery of indoor, outdoor and stylized scenes, and 3DGS-rendered depth (RGB-D) outputs. According to a YouTube creator summary, a four-step version generates a scene in about 6 seconds at 480p.\n\nThe page text available does not include a public code or weights release. The same creator summary says code and models are planned. It is currently a research project with a project page and an arXiv paper, and no product, API or pricing is listed.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
3D scene generator from text or images that works in pixel space rather than latent space. A four-step version generates a scene in about 6 seconds at 480p. Code and models are planned for release.
Closest neighbours by meaning, not just by category.
Model
Image-to-3D generator from Tsinghua and Tencent ARC Lab that builds meshes pixel-aligned to the input view.
Model · World Labs
World Labs' world model that generates and reconstructs explorable 3D worlds from images, text, video or 3D input.
Library · World Labs
World Labs tooling that turns a single image into an editable 3D environment with meshes, splats, physics and lighting.
Model
Research framework that turns posed images with instance masks and 3D boxes into per-object meshes for cluttered scenes.
Model
Research model that predicts layered, pixel-aligned 3D point clouds, including hidden geometry, from one image or video.
Model
Roblox research model that generates text-to-3D objects as separate part meshes from a user-defined part list.
