#novel view synthesis

The project offers a unique 3D smoothing and 2D Mip filter for Gaussian Splatting, eliminating artifacts for clean renderings. With enhancements from a densification metric, it improves view synthesis outcomes. Detailed setup instructions and rich dataset support, including Blender and Mip-NeRF 360 datasets, ensure robust experimentation and model evaluation.

FlowMap utilizes gradient descent for efficient camera pose and depth estimation, demonstrating versatility across datasets like Real Estate 10k and Tanks & Temples. It includes tools for view synthesis via modified 3D Gaussian Splatting, and offers a framework adaptable for photogrammetry purposes. With a Linux-friendly setup, pretrained options, and customizable Hydra configurations, it’s suitable for researchers and developers. Endorsed by leading institutions, FlowMap is both scientifically and practically significant.