GIRAFFE HD: A High-Resolution 3D-aware Generative Model
This work addresses the need for high-resolution, controllable image generation in computer vision and graphics, representing an incremental improvement over the existing GIRAFFE model.
The paper tackles the problem of low-resolution limitations in 3D-aware generative models by proposing GIRAFFE HD, which generates high-quality images at 512^2 resolution and above while maintaining controllable features like object rotation and scene camera pose.
3D-aware generative models have shown that the introduction of 3D information can lead to more controllable image generation. In particular, the current state-of-the-art model GIRAFFE can control each object's rotation, translation, scale, and scene camera pose without corresponding supervision. However, GIRAFFE only operates well when the image resolution is low. We propose GIRAFFE HD, a high-resolution 3D-aware generative model that inherits all of GIRAFFE's controllable features while generating high-quality, high-resolution images ($512^2$ resolution and above). The key idea is to leverage a style-based neural renderer, and to independently generate the foreground and background to force their disentanglement while imposing consistency constraints to stitch them together to composite a coherent final image. We demonstrate state-of-the-art 3D controllable high-resolution image generation on multiple natural image datasets.