Showing 7 of 7 projects
A hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras with modern features, loop closure, and dense reconstruction.
An end-to-end deep learning system for reconstructing complete 3D scenes (geometry and semantics) from posed 2D images.
A curated list of research papers and resources for scene understanding in computer vision, covering 3D reconstruction, layout estimation, and primitive detection.
A deep learning model for joint perception and motion prediction in autonomous driving using bird's eye view maps.
A TensorFlow implementation of Attend, Infer, Repeat (AIR), a generative model for fast scene understanding by reconstructing objects sequentially.
Estimates horizon lines from single images using deep learning models trained on diverse outdoor scenes.
Matlab code that converts RGBD images into CAD-like 3D models using surface prediction and POV-Ray rendering.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.