Compare CentiLeo vs. GET3D

CentiLeo is a highly efficient GPU path tracer designed for seamless integration with both 3ds Max and Cinema 4D, allowing users to easily manage complex lighting in their scenes. This advanced GPU renderer excels in delivering rapid unbiased path tracing, particularly for intricate lighting scenarios. Featuring out-of-core technology, CentiLeo can efficiently handle enormous scene assets, enabling the rendering of polygon counts, particles, and textures that exceed the limitations of GPU memory. The innovative technology extends the memory capacity for geometry and particles by four times and dramatically increases texture memory limits by a factor of 100. In addition, CentiLeo offers capabilities such as Interactive Preview Render, node-based material and shader editing, displacement mapping, motion blur, subsurface scattering, and rapid noise reduction tailored for multi-materials, glass objects, and mesh lights. Moreover, the software has received support from the Skolkovo Foundation, which has backed some of its research and development initiatives through grants, underscoring the commitment to advancing rendering technology. This combination of features makes CentiLeo an ideal choice for artists and designers looking to enhance their rendering workflows.

We create a three-dimensional signed distance field (SDF) and a textured field using two latent codes. DMTet is employed to derive a 3D surface mesh from the SDF, and we sample the texture field at the surface points to obtain color information. Our training incorporates adversarial losses focused on 2D images, specifically utilizing a rasterization-based differentiable renderer to produce both RGB images and silhouettes. To distinguish between genuine and generated inputs, we implement two separate 2D discriminators—one for RGB images and another for silhouettes. The entire framework is designed to be trainable in an end-to-end manner. As various sectors increasingly transition towards the development of expansive 3D virtual environments, the demand for scalable tools that can generate substantial quantities of high-quality and diverse 3D content has become apparent. Our research endeavors to create effective 3D generative models capable of producing textured meshes that can be seamlessly integrated into 3D rendering engines, thereby facilitating their immediate application in various downstream uses. This approach not only addresses the scalability challenge but also enhances the potential for innovative applications in virtual reality and gaming.