Geodesy

Quantum mechanics

Benchmark (surveying)

Voltage

Active shape model

Set (abstract data type)

Computer science

Code (set theory)

Natural language processing

Shape analysis (program analysis)

Physics

Segmentation

Mathematics

Geography

Text generation

Artificial intelligence

Geometry

Transformer

Programming language

Static analysis

Word (group theory)

Consistency (knowledge bases)

In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical contributions. First, we decouple the shape and color predictions for learning features in both texts and shapes, and propose the word-level spatial transformer to correlate word features from text with spatial features from shape. Also, we design a cyclic loss to encourage consistency between text and shape, and introduce the shape IMLE to diversify the generated shapes. Further, we extend the framework to enable text-guided shape manipulation. Extensive experiments on the largest existing text-shape benchmark [10] manifest the superiority of this work. The code and the models are available at https://github.com/liuzhengzhe/Towards-Implicit-Text-Guided-Shape-Generation.

Towards Implicit Text-Guided 3D Shape Generation