Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model
This addresses the need for fast and high-quality 3D asset creation from text prompts, with incremental improvements in speed and quality over existing methods.
The paper tackles the problem of slow and low-quality text-to-3D generation by proposing Instant3D, a feed-forward method that generates diverse 3D assets in 20 seconds, which is two orders of magnitude faster than previous optimization-based methods.
Text-to-3D with diffusion models has achieved remarkable progress in recent years. However, existing methods either rely on score distillation-based optimization which suffer from slow inference, low diversity and Janus problems, or are feed-forward methods that generate low-quality results due to the scarcity of 3D training data. In this paper, we propose Instant3D, a novel method that generates high-quality and diverse 3D assets from text prompts in a feed-forward manner. We adopt a two-stage paradigm, which first generates a sparse set of four structured and consistent views from text in one shot with a fine-tuned 2D text-to-image diffusion model, and then directly regresses the NeRF from the generated images with a novel transformer-based sparse-view reconstructor. Through extensive experiments, we demonstrate that our method can generate diverse 3D assets of high visual quality within 20 seconds, which is two orders of magnitude faster than previous optimization-based methods that can take 1 to 10 hours. Our project webpage: https://jiahao.ai/instant3d/.