Yingshuang Zou

Papers

Total Citations

H-Index

About

Yingshuang Zou is a rising researcher in computer vision and 3D scene understanding, with a focus on efficient semantic field learning for real-world applications such as autonomous navigation, augmented and virtual reality, and robotics. Her most notable contribution, "SLGaussian: Fast Language Gaussian Splatting in Sparse Views" (2025), addresses a critical limitation in existing 3D semantic field methods: their reliance on computationally expensive per-scene multi-view optimizations that fail under sparse view conditions. By introducing a novel framework that enables rapid language-aligned Gaussian splatting from limited viewpoints, Zou’s work significantly improves both efficiency and accuracy, making it highly relevant for dynamic, resource-constrained environments. Though early in her career, her research has already garnered attention, with her flagship paper accumulating citations and setting a foundation for future breakthroughs in sparse-view 3D comprehension. Zou’s innovative approach promises to advance how machines perceive and interact with complex, partially observed scenes, marking her as a promising voice in next-generation computer vision.