Jinming Song

Nanjing University of Information Science and Technology

Papers

Total Citations

H-Index

About

Jinming Song is a rising researcher in computer vision and 3D scene understanding, with a focus on panoramic perception and immersive reconstruction. His most notable work, "Pano3R," introduces a training-free framework for panoramic 3D reconstruction, directly addressing the critical challenge of adapting pinhole-based methods to 360° inputs. By eliminating the need for costly panoramic training data or model retraining, Song’s approach enables robust, generalizable 3D reconstruction from omnidirectional images—a key enabler for applications in robotics, augmented reality, and autonomous driving. While his work is early-stage, with the paper already garnering citations, it signals a significant contribution to bridging the gap between conventional 3D vision and emerging panoramic platforms. Song’s research is characterized by its practical, data-efficient philosophy, aiming to make advanced 3D perception accessible without the traditional overhead of large-scale annotated datasets. As the demand for holistic scene understanding grows, his contributions are poised to influence both academic research and real-world deployment in spatial computing and autonomous systems.