Nelson Durrant

Brigham Young University

Papers

1

Total Citations

6

H-Index

1

About

Nelson Durrant is a researcher at the forefront of computer vision and graphics, with a particular focus on novel view synthesis and inverse rendering in complex, real-world environments. His work addresses the challenging problem of reconstructing accurate 3D scenes from imagery degraded by natural phenomena. Durrant’s major contribution, exemplified in his highly cited paper **"RecGS: Removing Water Caustic With Recurrent Gaussian Splatting"** (2024, 6 citations), introduces a pioneering method to handle water caustics—the shifting light patterns that plague seafloor imaging. Unlike traditional 2D filtering or dataset-dependent approaches, RecGS leverages a recurrent architecture within the 3D Gaussian Splatting framework to dynamically separate and remove these distortions during the reconstruction process. This innovation allows for robust generalization to real-world underwater data without requiring pre-annotated training sets, directly improving the fidelity of 3D models for marine science and archaeology. By tackling a long-standing bottleneck in underwater computer vision, Durrant’s work demonstrates a powerful synergy between advanced neural rendering techniques and practical environmental sensing, marking him as a rising talent in applied 3D scene understanding.

Research Focus

Key Achievements

1
H-Index
1
Papers
6
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
<b>RecGS</b>: Removing Water Caustic With <b>Rec</b>urrent <b>G</b>aussian <b>S</b>platting
6 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 7
🏛 Institutions: Brigham Young University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 10 days ago