Dongyuan Li

Papers

Total Citations

H-Index

About

Dongyuan Li is a rising researcher at the forefront of computer vision, with a primary focus on 3D scene understanding and generative modeling. His most cited work, the 2024 survey "Diffusion Models in 3D Vision," has already garnered 2 citations, establishing him as a key voice in synthesizing the rapidly evolving intersection of diffusion-based generative AI and 3D perception. Li’s contributions center on advancing how machines perceive, reconstruct, and generate 3D environments from 2D inputs—critical for autonomous driving, robotics, and augmented reality. By systematically categorizing and analyzing diffusion models applied to tasks like 3D object generation, scene completion, and novel view synthesis, his survey provides a foundational roadmap for researchers navigating this emerging field. Li’s work is notable for its timely synthesis of complex methodologies, bridging the gap between generative AI and practical 3D vision applications. As his research gains traction, he is poised to influence both academic inquiry and real-world deployment of intelligent 3D systems, making him a promising figure to watch in the next wave of computer vision innovation.