Papers
1
Total Citations
3
H-Index
1
About
Jingwei Huang is a rising researcher at the forefront of computer vision and graphics, with a primary focus on advancing 3D scene representation and reconstruction under challenging visual conditions. His most notable contribution is the development of LLGS (Low-Light Gaussian Splatting), a pioneering unsupervised framework that adapts 3D Gaussian Splatting—a state-of-the-art technique for novel view synthesis—to function effectively in pure dark environments. While traditional Gaussian Splatting excels in well-lit scenes, it fails to represent color and detail when input images are severely underexposed. Huang’s key innovation lies in enabling multi-view optimization without requiring pre-enhanced images, directly tackling the color representation gap. This work, published in 2025, has already garnered 3 citations, signaling its early impact on the field. By bridging the gap between low-light image enhancement and 3D reconstruction, Huang’s research opens new avenues for applications in night-time robotics, autonomous navigation, and augmented reality. His approach not only improves visual fidelity in darkness but also reduces dependency on external preprocessing, marking a significant step toward robust, all-weather visual systems.
Research Focus
Key Achievements
Top Papers
- 1