Generation High resolution 3D model from natural language by Generative Adversarial Network
This addresses the problem of creating detailed 3D models from text for applications like computer graphics or virtual reality, but it appears incremental as it builds on prior low-resolution generation work.
The paper tackles generating high-resolution 3D shapes from natural language descriptions by proposing a two-step method that first generates low-resolution shapes and then refines them to high resolution using a Conditional Wasserstein GAN with a modified Critic, achieving improved faithfulness and quality as evaluated by numerical metrics.
We present a method of generating high resolution 3D shapes from natural language descriptions. To achieve this goal, we propose two steps that generating low resolution shapes which roughly reflect texts and generating high resolution shapes which reflect the detail of texts. In a previous paper, the authors have shown a method of generating low resolution shapes. We improve it to generate 3D shapes more faithful to natural language and test the effectiveness of the method. To generate high resolution 3D shapes, we use the framework of Conditional Wasserstein GAN. We propose two roles of Critic separately, which calculate the Wasserstein distance between two probability distribution, so that we achieve generating high quality shapes or acceleration of learning speed of model. To evaluate our approach, we performed quantitive evaluation with several numerical metrics for Critic models. Our method is first to realize the generation of high quality model by propagating text embedding information to high resolution task when generating 3D model.