A curated list of top-tier publications and resources for LiDAR-Visual fusion SLAM systems.
Awesome-LiDAR-Visual-SLAM is a curated GitHub repository listing academic papers, code, and datasets related to SLAM systems that fuse LiDAR and visual sensors. It addresses the problem of researchers and developers needing to manually survey a fragmented landscape of publications by providing a centralized, updated overview of state-of-the-art fusion algorithms.
Researchers, graduate students, and engineers working in robotics, autonomous vehicles, and embodied AI who are specifically focused on developing or implementing robust LiDAR-Visual SLAM systems.
Developers choose this resource because it saves significant literature review time by aggregating high-quality, peer-reviewed resources in one place. Its focus on fusion SLAM and active maintenance by an expert in the field ensures relevance and comprehensiveness.
A curated list of resources relevant to LiDAR-Visual-Fusion-SLAM
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Curates over 30 top-tier papers from 2015 to 2025, with direct links to papers and code, as seen in the detailed yearly lists including IROS, ICRA, and RAL publications.
Actively encourages contributions via pull requests, ensuring the list stays current with latest research, as highlighted in the README's contribution section and 2025 updates.
Dedicated exclusively to LiDAR-visual fusion SLAM, leveraging precise LiDAR and rich visual data for robust performance, per the introduction and multi-sensor fusion emphasis.
Only provides paper and code links without installation instructions, troubleshooting, or integration advice, leaving users to navigate complex setups independently.
Focuses solely on peer-reviewed publications, missing industry-grade tools and proprietary solutions that might be more relevant for commercial deployments.
Lists papers chronologically without summaries, comparisons, or performance benchmarks, requiring users to conduct their own evaluations of algorithm suitability.