Jiarui Meng
Papers
1
Total Citations
3
H-Index
1
About
Jiarui Meng is a rising researcher at the forefront of 3D computer vision, with a primary focus on scene understanding, representation learning, and their applications in autonomous driving, robotics, and augmented reality. His most notable contribution is the development of **InstanceGaussian**, a novel appearance-semantic joint Gaussian representation for 3D instance-level perception. This work directly tackles three critical challenges in 3D Gaussian Splatting: the imbalance between appearance and semantic features, inconsistencies in object boundaries, and difficulties in instance-level segmentation. By proposing a unified framework that jointly optimizes visual fidelity and semantic coherence, Meng’s approach enables more accurate and robust 3D scene parsing, a fundamental capability for intelligent systems navigating complex environments. Although his work is recent (2025), it has already garnered 3 citations, signaling early impact and interest from the community. Meng’s research bridges the gap between high-fidelity 3D reconstruction and high-level scene understanding, positioning him as a promising voice in the next generation of 3D perception researchers. His contributions are particularly relevant for students and engineers working on end-to-end perception pipelines for real-world autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1