3DGEN: A GAN-based approach for generating novel 3D models from image data
This addresses 3D model generation for applications in game design, video production, and product design, but appears incremental as it builds on existing methods.
The paper tackles 3D model generation from image data by proposing 3DGEN, which combines Neural Radiance Fields and GANs to generate plausible meshes for objects in the same category as training images, showing visible uplifts in quality compared to state-of-the-art baselines.
The recent advances in text and image synthesis show a great promise for the future of generative models in creative fields. However, a less explored area is the one of 3D model generation, with a lot of potential applications to game design, video production, and physical product design. In our paper, we present 3DGEN, a model that leverages the recent work on both Neural Radiance Fields for object reconstruction and GAN-based image generation. We show that the proposed architecture can generate plausible meshes for objects of the same category as the training images and compare the resulting meshes with the state-of-the-art baselines, leading to visible uplifts in generation quality.