#real-time rendering

GaussianDreamer facilitates the swift creation of detailed 3D models from text prompts by combining 2D and 3D diffusion models. Implementing advanced 3D Gaussian splatting, it enhances both speed and fidelity, rendering real-time 3D outputs in just 15 minutes using a single GPU. Through techniques like noise addition and color variation, it ensures 3D consistency and clarity. Suitable for animation and simulation integration, it allows for Unity export and avatar generation, providing utility across multiple applications.

The 4DGaussians project provides an efficient method for real-time and high-quality rendering of dynamic scenes using 4D Gaussian splatting. It optimizes setups and hyperparameters for datasets such as HyperNeRF and D-NeRF, offering minimal training times while supporting multiple view configurations. This project facilitates environment setup, data preparation, and model training using PyTorch. Check out the project's GitHub for scripts and further insights into rendering, evaluation, and checkpoint usage.

GauHuman utilizes monocular videos for effective Gaussian splatting with training times of 1-2 minutes and real-time rendering at up to 189 FPS. It offers detailed guidance on environment setup, training, and evaluation using a range of datasets including ZJU-Mocap-Refine and MonoCap. Compatibility with NVIDIA GPUs is mandatory, with comprehensive setup instructions provided. GauHuman excels in efficient rendering of human movements and integrates foundational technologies such as Gaussian-Splatting and HumanNeRF.

GaussianShader optimizes neural rendering for reflective surfaces using a simplified shading function applied to 3D Gaussians. This approach ensures high material and lighting fidelity at real-time speeds. Starting with neural 3D Gaussian spheres, it integrates shading attributes for precise view-dependent appearance capture. It also includes a differentiable environment lighting map to facilitate free-viewpoint rendering in diverse lighting conditions, proving effective on datasets like NeRF Synthetic and Tanks&Temples.