GeometryCrafter is a novel framework that estimates high-fidelity and temporally coherent point maps from open-world videos, enhancing 3D/4D reconstruction and depth-based applications. It utilizes a point map Variational Autoencoder (VAE) to effectively encode and decode point maps, achieving state-of-the-art accuracy and temporal consistency across diverse environments. The approach addresses limitations in traditional video depth estimation methods, providing improved geometric fidelity for various tasks.
+ geometry
point-maps ✓
video-analysis ✓
reconstruction ✓
machine-learning ✓