ZeroForge: Feedforward Text-to-Shape Without 3D Supervision

Kelly O. Marshall, Minh Pham, Ameya Joshi, Anushrut Jignasu, Aditya Balu +2 more
6/14/2023
cs.CV

No official code found. Best implementation: Km3888/ZeroForge (6 stars, last commit 2023-08-02).

Abstract

Current state-of-the-art methods for text-to-shape generation either require supervised training using a labeled dataset of pre-defined 3D shapes, or perform expensive inference-time optimization of implicit neural representations. In this work, we present ZeroForge, an approach for zero-shot text-to-shape generation that avoids both pitfalls. To achieve open-vocabulary shape generation, we require careful architectural adaptation of existing feed-forward approaches, as well as a combination of data-free CLIP-loss and contrastive losses to avoid mode collapse. Using these techniques, we are able to considerably expand the generative ability of existing feed-forward text-to-shape models such as CLIP-Forge. We support our method via extensive qualitative and quantitative evaluations

View on arXivView PDF

Code Implementations(1)

Km3888/ZeroForgeCommunity100%

Code for ZeroForge submission

60PythonNov 29, 20223 years ago

Similar Papers

DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation

84% match1 repo452023

ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model

83% match1 repo282022

TPA3D: Triplane Attention for Fast Text-to-3D Generation

83% match1 repo42023

EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation

83% match1 repo372023

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis

82% match1 repo902024

A Survey On Text-to-3D Contents Generation In The Wild

81% match2024

Cite this paper

@article{marshall2023zeroforge,
  title  = {ZeroForge: Feedforward Text-to-Shape Without 3D Supervision},
  author = {Kelly O. Marshall and Minh Pham and Ameya Joshi and Anushrut Jignasu and Aditya Balu and Adarsh Krishnamurthy and Chinmay Hegde},
  year   = {2023},
  eprint = {2306.08183},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.08183v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.08183.svg)](https://codeofpaper.com/paper/2306.08183)

Discussion