ClipMatrix: Text-controlled Creation of 3D Textured Meshes

09/27/2021
by   Nikolay Jetchev, et al.
0

If a picture is worth thousand words, a moving 3d shape must be worth a million. We build upon the success of recent generative methods that create images fitting the semantics of a text prompt, and extend it to the controlled generation of 3d objects. We present a novel algorithm for the creation of textured 3d meshes, controlled by text prompts. Our method creates aesthetically pleasing high resolution articulated 3d meshes, and opens new possibilities for automation and AI control of 3d assets. We call it "ClipMatrix" because it leverages CLIP text embeddings to breed new digital 3d creatures, a nod to the Latin meaning of the word "matrix" - "mother". See the online gallery for a full impression of our method's capability.

READ FULL TEXT

page 1

page 2

page 4

research
06/13/2020

Convolutional Generation of Textured 3D Meshes

Recent generative models for 2D images achieve impressive visual results...
research
05/01/2008

Morphing of Triangular Meshes in Shape Space

We present a novel approach to morph between two isometric poses of the ...
research
04/24/2023

TextMesh: Generation of Realistic 3D Meshes From Text Prompts

The ability to generate highly realistic 2D images from mere text prompt...
research
03/21/2023

3D-CLFusion: Fast Text-to-3D Rendering with Contrastive Latent Diffusion

We tackle the task of text-to-3D creation with pre-trained latent-based ...
research
03/02/2017

Toward Controlled Generation of Text

Generic generation and manipulation of text is challenging and has limit...
research
12/06/2019

NASA: Neural Articulated Shape Approximation

Efficient representation of articulated objects such as human bodies is ...
research
06/06/2023

Dance Generation by Sound Symbolic Words

This study introduces a novel approach to generate dance motions using o...

Please sign up or login with your details

Forgot password? Click here to reset