Point-EOpenAI
|
TRELLISMicrosoft
|
|||||
| Point-E | TRELLIS | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
Point-E:
About
While recent work on text-conditional 3D object generation has shown promising results, the state-of-the-art methods typically require multiple GPU-hours to produce a single sample. This is in stark contrast to state-of-the-art generative image models, which produce samples in a number of seconds or minutes. In this paper, we explore an alternative method for 3D object generation which produces 3D models in only 1-2 minutes on a single GPU. Our method first generates a single synthetic view using a text-to-image diffusion model and then produces a 3D point cloud using a second diffusion model which conditions the generated image. While our method still falls short of the state-of-the-art in terms of sample quality, it is one to two orders of magnitude faster to sample from, offering a practical trade-off for some use cases. We release our pre-trained point cloud diffusion models, as well as evaluation code and models, at this https URL.
|
TRELLIS:
About
TRELLIS is a research-oriented 3D asset generation model and Python codebase from Microsoft Research. It accepts text or image prompts and produces 3D assets as meshes, 3D Gaussians, and radiance fields. The project includes pretrained image- and text-conditioned models, inference pipelines, tools for creating asset variants and editing selected regions, training code, and a dataset toolkit. Researchers and developers can run it locally on Linux with a compatible NVIDIA GPU, or use a browser-based Microsoft Foundry or Hugging Face demo. Installation guidance specifies Python and CUDA, with at least 16 GB of GPU memory for the tested setup. The project website describes its materials as intended for academic and research purposes, not commercial use; users should review the separate repository and component licenses before use.
|
|||||
Point-E:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
TRELLIS:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Supported
Cloud
Not Supported
On-Premises
Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Point-E:
Audience
Anyone searching for a system for generating 3D point clouds from complex prompts
|
TRELLIS:
Audience
Researchers and developers working on generative 3D graphics, 3D asset creation, and related model experimentation.
|
|||||
Point-E:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
TRELLIS:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
Point-E:
API
Offers API
Not Supported
|
TRELLIS:
API
Offers API
Supported
|
|||||
Point-E:
Screenshots and Videos |
TRELLIS:
Screenshots and Videos |
|||||
Point-E:
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
TRELLIS:
Pricing
Free
Open source
Free Version
Supported
Free Trial
Not Supported
|
|||||
Point-E:
Reviews/
|
TRELLIS:
Reviews/
|
|||||
Point-E:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
TRELLIS:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Point-E:
Company InformationOpenAI
Founded: 2015
United States
openai.com/research/point-e
|
TRELLIS:
Company InformationMicrosoft
Founded: 1975
United States
microsoft.github.io/TRELLIS/
|
|||||
Point-E:
Alternatives |
TRELLIS:
Alternatives |
|||||
|
Point-E:
|
TRELLIS:
|
|||||
|
Point-E:
|
TRELLIS:
|
|||||
| Point-E: | TRELLIS: | |||||
|
Point-E:
|
TRELLIS: | |||||
Point-E:
Categories |
TRELLIS:
Categories |
|||||
Point-E:
Integrations
No info available.
|
TRELLIS:
Integrations
No info available.
|
|||||
|
Point-E:
|
TRELLIS:
|