HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation

Antoine Mercier, Ramin Nakhli, Mahesh Reddy, Rajeev Yasarla, Hong Cai, Fatih Porikli, Guillaume Berger

HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation: 11 upvotes on Hugging Face Daily Papers, #9 of 9 papers on 2024-01-17. Day-by-day upvote history.

Despite the latest remarkable advances in generative modeling, efficient generation of high-quality 3D assets from textual prompts remains a difficult task. A key challenge lies in data scarcity: the most extensive 3D datasets encompass merely millions of assets, while their 2D counterparts contain billions of text-image pairs. To address this, we propose a novel approach which harnesses the power of large, pretrained 2D diffusion models. More specifically, our approach, HexaGen3D, fine-tunes a pretrained text-to-image model to jointly predict 6 orthographic projections and the corresponding latent triplane. We then decode these latents to generate a textured mesh. HexaGen3D does not require per-sample optimization, and can infer high-quality and diverse objects from textual prompts in 7 seconds, offering significantly better quality-to-latency trade-offs when comparing to existing approaches. Furthermore, HexaGen3D demonstrates strong generalization to new objects or compositions.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.