Monocular Depth Estimation & Video Depth

3 repos

This cluster focuses on single-image and video-based depth estimation techniques, with particular emphasis on diffusion models and neural approaches for inferring 3D scene geometry from 2D visual input. The repositories span foundational depth prediction architectures, video frame analysis for temporal depth consistency, and generative diffusion-based methods for depth map synthesis. Learners here will encounter computer vision fundamentals, 3D scene understanding, and modern deep learning approaches to the monocular depth problem.

Related clusters