OpenAI has released Point-E, an open source AI system that can generate 3D point clouds given a text prompt.

The results aren't true 3D models, but they achieve a similar effect: The AI tool generates 2D video frames that maintain ...

This episode looks at the "point clouds" for 3D data visuals used in architecture, archaeology, and autonomous driving. Plus, robots learn new moves.

OpenAI releases Point-E, which is like DALL-E but for 3D modeling Its resolution isn't great but it's up to two magnitudes faster than competing systems.

Point clouds are what 3D scanners create when an object is scanned, and to become useful, those point clouds are usually post-processed into 3D models (specifically, meshes) like an .obj or .stl file.

Recently, tech giants such as Tencent, Apple, and Google have made significant moves, injecting new vitality into the AI ...

Then, a 3D point cloud is generated, which is easier to synthesize hence the reduced load on GPUs, though it doesn’t capture smaller details hence the trade-off mentioned in the paper.

This means that Shap·E can create high-quality 3D assets with fine-grained textures and complex shapes, unlike current models that only output point clouds or voxels.