“EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation” by Liu, Hu, Hui, Qi, Cohen-Or, et al. …
Conference:
Type(s):
Title:
- EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation
Session/Category Title: Texture Magic
Presenter(s)/Author(s):
Abstract:
This paper presents a new text-guided technique for generating 3D shapes. The technique leverages a hybrid 3D shape representation, combining the strengths of explicit and implicit representations. Specifically, the explicit stage controls the generated topology of the 3D shape and allows local manipulations, while the implicit stage refines the shape and paints it with plausible colors. Also, the hybrid approach separates shape and color, ensuring shape-color consistency. Unlike existing state-of-the-art methods, our technique achieves high-fidelity shape generation from natural-language descriptions without the need for time-consuming per-shape optimization or reliance on human-annotated texts during training or test-time optimization. Furthermore, we demonstrate the extension of our approach to generate indoor scenes with consistent styles using text-induced 3D shapes. Through extensive experiments, we demonstrate the compelling quality of our results and the high coherency of our generated shapes with the input texts, surpassing the performance of existing methods by a significant margin.
