Shuangfu Song

Tongji University

Papers

2

Total Citations

9

H-Index

1

About

Shuangfu Song is a rising researcher in robotics and 3D computer vision, whose work focuses on advancing neural implicit representations for large-scale autonomous mapping. His primary contributions lie in developing novel signed distance field (SDF) frameworks that overcome the limitations of traditional projective-distance supervision. Song’s most influential work, **N³-Mapping** (2024, 8 citations), introduced a normal-guided, non-projective neural SDF approach that achieves accurate and dense 3D reconstruction across expansive environments—a critical capability for autonomous robot navigation. Building on this, his **UN³-Mapping** (2025) integrates uncertainty estimation into the neural mapping pipeline, enabling robots to not only build high-quality maps but also assess their reliability. This hybrid representation addresses a key challenge in field robotics: robust operation under sensor noise and dynamic conditions. Though early in his career, Song’s work is already recognized for pushing the boundaries of implicit neural mapping from theoretical novelty toward practical deployment. His research directly supports safer, more perceptive autonomous systems, making him a notable emerging voice in the intersection of neural geometry learning and real-world robotic perception.

Research Focus

Key Achievements

1
H-Index
2
Papers
9
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
N$^{3}$-Mapping: Normal Guided Neural Non-Projective Signed Distance Fields for Large-Scale 3D Mapping
8 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: Tongji University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago