A curated list of papers, software, and resources for 3D reconstruction from images, covering SLAM, SfM, and MVS.
Awesome 3D Reconstruction List is a curated collection of academic papers, tutorials, open-source software, and datasets focused on 3D reconstruction from images. It covers key areas like Structure-from-Motion (SfM), Simultaneous Localization and Mapping (SLAM), and Multi-View Stereo (MVS), serving as a reference hub for the computer vision community.
Researchers, graduate students, and developers in computer vision and robotics who need a structured overview of state-of-the-art methods and tools for 3D reconstruction.
It saves time by aggregating and categorizing essential resources in one place, provides license and language details for software, and includes datasets for benchmarking, making it a trusted starting point for exploration and implementation.
A curated list of papers & resources linked to 3D reconstruction from images.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Organizes content into clear categories like SLAM, SfM, and MVS, making it easy to navigate specific subfields. This is evidenced by the detailed table of contents in the README.
Aggregates key papers, tutorials, open-source software, and datasets in one place, saving research time. The README includes sections for each, such as 'OpenSource software resources' and 'Datasets with ground truth'.
Lists language and license information for open-source software, helping developers assess compatibility and legal use. Examples include tables with 'Language' and 'License' columns for SfM and MVS tools.
Part of the Awesome list ecosystem with a contributing guide, ensuring community maintenance and reliability. The README has a 'Contributing' section and an Awesome badge.
Explicitly states it is 'not exhaustive' in the README, so it may miss niche or emerging resources, requiring supplemental searches.
As a curated list, updates depend on community contributions, which can lead to outdated links or obsolete tools over time, especially in fast-evolving fields like machine learning MVS.
Uses alphabetical order for fairness, but this doesn't highlight the most impactful or high-quality resources, leaving users to sift through entries without quality rankings.
While it lists tutorials, it doesn't provide structured sequences or practical examples for beginners to build skills progressively, relying on external content.