Single Image to High-Quality 3D Object via Latent Features
This addresses the challenge of fast, detailed 3D asset generation for digital applications, but it appears incremental as it builds on existing image-to-3D methods with a novel pipeline.
The paper tackles the problem of generating high-quality 3D objects from single images by introducing LatentDreamer, a framework that uses a pre-trained variational autoencoder to map 3D geometries to latent features, achieving high fidelity and completing generation in about 70 seconds.
3D assets are essential in the digital age. While automatic 3D generation, such as image-to-3d, has made significant strides in recent years, it often struggles to achieve fast, detailed, and high-fidelity generation simultaneously. In this work, we introduce LatentDreamer, a novel framework for generating 3D objects from single images. The key to our approach is a pre-trained variational autoencoder that maps 3D geometries to latent features, which greatly reducing the difficulty of 3D generation. Starting from latent features, the pipeline of LatentDreamer generates coarse geometries, refined geometries, and realistic textures sequentially. The 3D objects generated by LatentDreamer exhibit high fidelity to the input images, and the entire generation process can be completed within a short time (typically in 70 seconds). Extensive experiments show that with only a small amount of training, LatentDreamer demonstrates competitive performance compared to contemporary approachs.