2024/01/15 by Antoine Mercier, Mercier, Antoine, Ramin Nakhli +12 · 1 voice · 4 citations
Computer Science · Engineering · #Generative Adversarial Networks and Image Synthesis #3D Shape Modeling and Analysis #Image Processing and 3D Reconstruction
paper · pdf · doi:10.48550/arxiv.2401.07727
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.